🔥Professional Certificate Course In AI And Machine Learning by IIT Kanpur (India Only): www.simplilearn.com/iitk-professional-certificate-course-ai-machine-learning?AugustTubebuddyExpPCPAIandML&Comments& 🔥AI Engineer Masters Program (Discount Code - YTBE15): www.simplilearn.com/masters-in-artificial-intelligence?SCE-AIMasters&Comments& 🔥AI & Machine Learning Bootcamp(US Only): www.simplilearn.com/ai-machine-learning-bootcamp?MachineLearningscribe&Comments& 🔥 Purdue Post Graduate Program In AI And Machine Learning: www.simplilearn.com/pgp-ai-machine-learning-certification-training-course?MachineLearningscribe&Comments&
**Summary**: - machine learning is the general term for when computers learn from data - there are lots of different ways ("algorithms") that machines can learn - the algorithms can be grouped into supervised, unsupervised, and reinforcement algorithms* - the data that you feed to a machine learning algorithm can be input-output pairs or just inputs - supervised learning algorithms require input-output pairs (i.e. they require the output) - unsupervised learning requires only the input data (not the outputs) - here is how, in general, supervised algorithms work: - you feed it an example input, then the associated output - you repeat the above step many many times - eventually, the algorithm picks up a pattern between the inputs and outputs - now, you can feed it a brand new input, and it will predict the output for you - here is how, in general, unsupervised algorithms work: - you feed it an example input (without the associated output) - you repeat the above step many times - eventually, the algorithm clusters your inputs into groups - now, you can feed it a brand new input, and the algorithm will predict which cluster it belongs with * the first example in this video used the k-nearest neighbor algorithm, which is a supervised machine learning algorithm Hope that was useful to someone! Thanks for the video, really enjoyed it!! :)
Quite great. An Amazing one explaining the ML basis.!! 1. Supervised learning. 2. Supervised learning after Feedback (Rein inforced learning) 3. Unsupervised learning.
Wow! You got all the answers right. Thanks for your kind comment as well. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
We're so glad that you enjoyed your time learning with us! If you're interested in continuing your education and developing new skills, take a look at our course offerings in the description box. We're confident that you'll find something that piques your interest!
WooHoo! We are so happy you love our videos. Please do keep checking back in. We put up new videos every week on all your favorite topics. Do subscribe to our channel to stay posted on upcoming tutorials. Cheers!
wow! this is my first time actually researching this topic being a computer science student. i have got to say, this really brightened my mood and brought some light to my day/mind regarding my major! :) awesome stuff!
We are glad you found our video helpful, Adnan. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
This video is quiet frankly down to point. I was even excited when I begun this field and the different things you could indulge in and improve for a business. It really is helping me and my career. I am even starting my own channel to breakdown some of the concepts that I found hard to understand about different algorithms and how they work. Check it out and for any starters, do tell me what you find hard at first to grasp when begging into the field ☺️
WooHoo! We are so happy you love our videos. Please do keep checking back in. We put up new videos every week on all your favorite topics. Whenever you have the time, you must also check out our blog page @simplilearn.com and tell us what you think. Have a good day!
"Wow! You got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of ""fraud"" and ""not fraud"". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'."
Yes, it is indeed a game changer. Check out our Machine learning playlist to know about the fundamentals courses and algorithms: czcams.com/video/ukzFI9rgwfU/video.html. For rest of the course, you need to sign up for our Machine learning Certification Training Course: www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course.
Machine learning is taking over the world- and with that, there is a growing need among companies for professionals to know the ins and outs of machine learning. You can start with this amazing playlist which helped a lot of people: czcams.com/video/ukzFI9rgwfU/video.html This playlist will provide you with the solid basic knowledge of Machine learning and it types with examples. It has videos both in R and Python. If you want to go further and get certified in Machine learning, check this out: www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course.
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
1) Facebook photo recognition based on tags in an example of supervised learning 2) NetFlix Movie recommendation is an example of unsupervised learning 3) Bank Fraud Detection is an example of reinforcement learning
Great Video . Thanks Much. Quiz answers 1. Supervised - Naivebayes algorithm with tagged images (or) can be Reinforcement too due to images which will be a very expensive algorithm 2. Supervised - K-nearest neighbors -alogrithm- 3. Unsupervised -
A real life problem which may need AI and ML: Examination Paper Evaluation/Correction which has descriptive questions. Two things : The accuracy level of earlier answers can be used to predict the confidence of accuracy of later answers. 2. Based on the other answers, a answer can be evaluated.
1. FB case: Supervised scenario (photo tags become labels) 2. Netflix case: Supervised scenario (like and dislike of a movie/show become the label) 3. Bank fraud case: Unsupervised scenario
Hey Dipendra, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Machine learning is taking over the world- and with that, there is a growing need among companies for professionals to know the ins and outs of machine learning. You can start with this amazing playlist which helped a lot of people: czcams.com/video/ukzFI9rgwfU/video.html This playlist will provide you with the solid basic knowledge of Machine learning and it types with examples. It has videos both in R and Python. If you want to go further and get certified in Machine learning, check this out: www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course.
@@poojaritulasi7680 Hi Poojari, machine learning is used in the various fields now. We recommend you check out the below link to know about Machine Learning and why it matters a lot: www.simplilearn.com/what-is-machine-learning-and-why-it-matters-article.
Wow! You got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Well! First of all thanks for this wonderful and informative video. The answer to the questions in the video might be 1.supeervised 2. supervised 3 . unsupervised Am I correct?
Wow! You got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Exactly! Search engines work based on Machine Learning concepts. Machine learning is taking over the world- and with that, there is a growing need among companies for professionals to know the ins and outs of machine learning. You can start with this amazing playlist which helped a lot of people: czcams.com/video/ukzFI9rgwfU/video.html This playlist will provide you with the solid basic knowledge of Machine learning and it types with examples. It has videos both in R and Python. If you want to go further and get certified in Machine learning, check this out: www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course.
Wow! You got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
@@SimplilearnOfficial If you use the decision tree by using existing features to classify a transaction as fraud (1) and no-fraud (0) than you are using a supervised learning based on classification. Right?
Hi, you got everything right. Kudos! Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious-looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
Hey Sanjeev, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Amazing video. Thank you Simplilearn. Example where I see application of machine learning could be CZcams itself. Once I watch a video on cooking, all recommendations on cooking video starts popping up!
S1 - Supervised - the labels are the faces of friendsS2 - Supervised - the labels are based on past views and sentiments of movies watched S3 - Unsupervised - no perceived labels available; based on outliers
Wow! you got it all right. Below are the right answers and explanation for the same. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Amazing amazing video! I have shared with many friends over WhatsApp, can't thank you enough. Quiz answer - scenario 1 is supervised, scenario 2 is supervised, and scenario 3 is unsupervised?
Wow! You got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
In my point of view 1- Scenario will be using the reinforcement learning. the reason is in the reinforcement example which is explained based on that only i am telling. 2 - scenario will be using the supervised learning. 3 - scenario will be using the unsupervised learning. If it's wrong please correct me. Thanks Simplilearn
Thanks for replying to the quiz Chaitanya. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Hi Pratibha, you got all the answers correct. Kudos. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
@@SimplilearnOfficial I am a massive fan of visual aids and numerous example driven content and interesting narratives in learning and kudos to SL I love the headfirst set of books which heavily uses stories and visual aids I have a question.I am looking to sign up for a course in AI AND ML. My question is if lectures n SL will be heavily based on visual narrations and interesting examples throughout the course ? IF SO,that would be truly wonderful and clutter breaking
That's great to hear it. Our courses do have visual narrations with 15+ real life industry projects. If you are interested to take up a more structured and formal course, you can find the details here: www.simplilearn.com/artificial-intelligence-introduction-for-beginners-training-course.
"Wow! You got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of ""fraud"" and ""not fraud"". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'."
@@SimplilearnOfficial Why is scenario 3 unsupervised learning? How does the system know that sth is "fraud" without being fed in previous cases which were called "fraud"? Like it has to know the features that make sth "fraud" before it can identify sth as "fraud"
@@angelflyinghigh1300 Hi Lucia, I would recon it (for example) compares properties of many transactions and puts the common ones in groups and thus sees which properties are anomalies (like, really big transaction amounts, or a never used bank account located far away, or many many small transactions with unclear description). But, that's just my two cents, I'm far from knowledgeable of Machine learning :)
Hi Isha, you almost got everything right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Hi Amilcar, we are glad that you found our video helpful and informative. Thank you for your kind words. Spread the word by liking, sharing and subscribing to our channel! Cheers :).
This Knowledge will help us Forever in Life, School Rote Learning is for a Short Period of Time which cannot help us, we can just get Marks and that's all, but knowledge will be with us Forever.
Great to hear it. This playlist will provide you with the solid basic knowledge of Machine learning and it types with examples. It has videos both in R and Python. If you want to go further and get certified in Machine learning, check this out: www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course.
Hi Sagar, you got everything right. Kudos! Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious-looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Here are the answers to the quiz with the explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
"Wow! You got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of ""fraud"" and ""not fraud"". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'."
"Wow! You got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of ""fraud"" and ""not fraud"". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'."
Thanks for replying to the quiz, Mustafa. You almost got the right answer. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Some of the best examples are youtube,twitter,flipcart....etc., in which these kind apps extract the content for us based on our past search data and preferences
Greetings! Thank you for your kind words. Spread the word by liking, sharing and subscribing to our channel! Cheers :). You can also explore our playlists for more Machine Learning Videos - czcams.com/video/ukzFI9rgwfU/video.html
Hi Anjaney, you almost got everything right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
@@SimplilearnOfficial In scenario 3, if you say the suspicious transactions are not defined. Does that means the system might know the valid transaction.?
This means that the model will study the pattern, evaluate whether the transaction done is normal as per the customer history and hence detect a suspicious transaction.
Hi Sitaram, thanks for replying to the quiz. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
@@@SimplilearnOfficial fraud transactions to be reinforcement learning right ( as it gives a negative feedback when some enters their data incorrectly )
This was very helpful, It has been hard grasping the idea we have managed to create machines, or scripts, that run mostly off of numbers and organization, to "learn"
@Simplilearn Thank you for this video! Shows the power of simplicity and your ability to simplify things. And asking people to comment on the 3 scenarios, great engagement strategy! 🙂
We are glad you found our video helpful, Maini. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
"Wow! You got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of ""fraud"" and ""not fraud"". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'."
Google crowdsource is the best example of machine learning to understand easily by a layman and also contribute. This will help to make better for different Google products like translate, maps, photos, searching and finding, etc.
Hi Neha, Below are the right answers and explanation for the quiz. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'
Hey Manasi, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Hi Mainak, we are glad you found our video helpful and informative. Do show your love by subscribing our channel using this link: czcams.com/users/Simplilearn and don't forget to hit the like button as well. Cheers!
You can train your machine learning model for image classification even without writing any code in an Android app called Pocket AutoML. It trains a model right on your phone without sending your photos to some "cloud" so it can even work offline.
Hi Soumyadeep, you got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Hi Victoria, we are glad you found our video helpful. Do subscribe to our channel and get our new video updates directly into your email. If you have any questions related to these videos, you can post in the comments section, we will clear your queries/doubts.
The video was quite interesting and informative. I would like to be your part of learning ML. It's very easy to understand how ML algorithms work. Thanks for it.
Hey Natalie, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
Deep Neural network concepts have been implemented for CZcams recommendation. For more detailed explanation, go through this blog: towardsdatascience.com/how-youtube-recommends-videos-b6e003a5ab2f
Hi Karthick, thanks for your reply to the quiz. You are almost right about everything and here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
@@SimplilearnOfficial hey tx for reply. But I was in little bit confused regarding the second scenario. .tx for nice explanation. ..hope for the more best quizs and tutorials too
Hi Harry, thanks for replying to the quiz. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Hi Nitesh, you got everything right. Kudos! Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Hi Onkar, Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious-looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Amazing video! I was getting headache learning the same topic from a coding site, I guess there is more than one ways if understanding things. Thank you!
We are glad you found our video helpful, Sakshi. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
Wow! You got all the answers right. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Scenario 1 is supervised earning because machine know the data(both friend photo and their name). 2. Netflix is same as person identify song (high intensity high tempo ) 3. Fraud is unsupervised I guess. By the way video is good. It's wow in one word
Hi Amogha, you are absolutely right about your answer and explanation. We really appreciate your kind comment. Do show your love by subscribing our channel using this link: czcams.com/users/Simplilearn and don't forget to hit the like button as well. Cheers!
@@SimplilearnOfficial Hi a quick question, should the 3rd one be case of reinforcement learning because transactions are very important and there needs to be a feedback mechanism to recorrect if there is a false positive or false negative ?
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
Great teacher. Great teaching skills. Try to add quiz question after explaining a concept on your upcoming videos, it really helps us to test our understanding on that topic. By d way great explanation =.
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
Thanks for replying to the quiz Chaitanya. Here are the answers with explanation. Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning. Scenario 2: Recommending new songs based on someone’s past music choices Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs). This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features. Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
🔥Professional Certificate Course In AI And Machine Learning by IIT Kanpur (India Only): www.simplilearn.com/iitk-professional-certificate-course-ai-machine-learning?AugustTubebuddyExpPCPAIandML&Comments&
🔥AI Engineer Masters Program (Discount Code - YTBE15): www.simplilearn.com/masters-in-artificial-intelligence?SCE-AIMasters&Comments&
🔥AI & Machine Learning Bootcamp(US Only): www.simplilearn.com/ai-machine-learning-bootcamp?MachineLearningscribe&Comments&
🔥 Purdue Post Graduate Program In AI And Machine Learning: www.simplilearn.com/pgp-ai-machine-learning-certification-training-course?MachineLearningscribe&Comments&
G.
**Summary**:
- machine learning is the general term for when computers learn from data
- there are lots of different ways ("algorithms") that machines can learn
- the algorithms can be grouped into supervised, unsupervised, and reinforcement algorithms*
- the data that you feed to a machine learning algorithm can be input-output pairs or just inputs
- supervised learning algorithms require input-output pairs (i.e. they require the output)
- unsupervised learning requires only the input data (not the outputs)
- here is how, in general, supervised algorithms work:
- you feed it an example input, then the associated output
- you repeat the above step many many times
- eventually, the algorithm picks up a pattern between the inputs and outputs
- now, you can feed it a brand new input, and it will predict the output for you
- here is how, in general, unsupervised algorithms work:
- you feed it an example input (without the associated output)
- you repeat the above step many times
- eventually, the algorithm clusters your inputs into groups
- now, you can feed it a brand new input, and the algorithm will predict which cluster it belongs with
* the first example in this video used the k-nearest neighbor algorithm, which is a supervised machine learning algorithm
Hope that was useful to someone!
Thanks for the video, really enjoyed it!! :)
Wow! This is one of the best summaries!
Thanks for the valuable input!
Do subscribe to our channel to stay posted on upcoming tutorials. Cheers!
@@SimplilearnOfficial Thank you! Definitely will, I love you guys' videos! :) Great job and keep it up!
Greetings! Thank you for your kind words. Spread the word by liking, sharing and subscribing to our channel! Cheers :)
i need help
Yes, what could we do for you?
Quite great. An Amazing one explaining the ML basis.!!
1. Supervised learning.
2. Supervised learning after Feedback (Rein inforced learning)
3. Unsupervised learning.
Wow! You got all the answers right. Thanks for your kind comment as well. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Labeled =supervised
Unlabeled= Un-supervised
And finally
Enforcement Learning = Learning from results and upgrading . Tq for the explanation
We're so glad that you enjoyed your time learning with us! If you're interested in continuing your education and developing new skills, take a look at our course offerings in the description box. We're confident that you'll find something that piques your interest!
Literally learnt more from you than 4 years in college
We are so grateful for your kind words. Also, subscribe to our channel and stay tuned for more videos. Cheers!
Is machine learning this much interesting in college also
…yet you still misspelled ‘learned,’ if only there was a video for that…
😁👍
/
I am from a health care background, but I could effortlessly understand everything she said. Excellent introduction.
WooHoo! We are so happy you love our videos. Please do keep checking back in. We put up new videos every week on all your favorite topics. Do subscribe to our channel to stay posted on upcoming tutorials. Cheers!
wow! this is my first time actually researching this topic being a computer science student. i have got to say, this really brightened my mood and brought some light to my day/mind regarding my major! :) awesome stuff!
Glad you enjoyed it! Thank you for watching!
I'm impressed by the way you taught. Teacher should to be like you.
We are glad you found our video helpful, Adnan. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
@@SimplilearnOfficial yes, already did. Thanks.🙏
@@AdnanKhan-iz9zb e3
@@AdnanKhan-iz9zb e3
@@SimplilearnOfficial re Jo inIn
This video is quiet frankly down to point. I was even excited when I begun this field and the different things you could indulge in and improve for a business. It really is helping me and my career. I am even starting my own channel to breakdown some of the concepts that I found hard to understand about different algorithms and how they work. Check it out and for any starters, do tell me what you find hard at first to grasp when begging into the field ☺️
WooHoo! We are so happy you love our videos. Please do keep checking back in. We put up new videos every week on all your favorite topics. Whenever you have the time, you must also check out our blog page @simplilearn.com and tell us what you think. Have a good day!
youtube recommended videos are the biggest example of machine learning , bcoz it recommends us videos on the basis of our history. AM I CORRECT?
Yes, you are absolutely correct. Search engine uses Machine learning algorithm to do the recommendation system. Thanks.
And that is what machine learning does
Well explained by this video :)
Scenario 1: Supervised Learning.
Scenario 2: Supervised Learning.
Scenario 3: Unsupervised Learning.
"Wow! You got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of ""fraud"" and ""not fraud"". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'."
1st & 2nd -supervised learning
3rd is Reinforced learning.
Thanku , you teach us great 🙏
Thanks for watching our video and sharing your thoughts. Do subscribe to our channel and stay tuned for more. Cheers!
The recommended videos which we are getting in the CZcams PAGE is one of the live examples of machine learning !!
You are right about that!
Machine learning is a game changer 📈
Yes, it is indeed a game changer. Check out our Machine learning playlist to know about the fundamentals courses and algorithms: czcams.com/video/ukzFI9rgwfU/video.html. For rest of the course, you need to sign up for our Machine learning Certification Training Course: www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course.
Want to Enroll & Get Certified ,, Who are best institute in NCR with affordable Price with high placement
Machine learning is taking over the world- and with that, there is a growing need among companies for professionals to know the ins and outs of machine learning. You can start with this amazing playlist which helped a lot of people: czcams.com/video/ukzFI9rgwfU/video.html
This playlist will provide you with the solid basic knowledge of Machine learning and it types with examples. It has videos both in R and Python. If you want to go further and get certified in Machine learning, check this out: www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course.
I am reading 21 lessons for 21st century ..these words are often coming ...it really helpful
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
1) Facebook photo recognition based on tags in an example of supervised learning
2) NetFlix Movie recommendation is an example of unsupervised learning
3) Bank Fraud Detection is an example of reinforcement learning
Thanks for watching our video and sharing your thoughts. Do subscribe to our channel and stay tuned for more. Cheers!
Loved the video..it's very informative and insightful under 8 mins..
Quiz Answers: 1st and 2nd are supervised while 3rd is unsupervised
Great Video . Thanks Much.
Quiz answers
1. Supervised - Naivebayes algorithm with tagged images (or) can be Reinforcement too due to images which will be a very expensive algorithm
2. Supervised - K-nearest neighbors -alogrithm-
3. Unsupervised -
Thanks for watching our video and sharing your thoughts. Do subscribe to our channel and stay tuned for more. Cheers!
A real life problem which may need AI and ML: Examination Paper Evaluation/Correction which has descriptive questions. Two things : The accuracy level of earlier answers can be used to predict the confidence of accuracy of later answers. 2. Based on the other answers, a answer can be evaluated.
It is certainly a good use case for Machine Learning.
youtube itself is the best example of machine learning ..because it automatically recommends the videos based on our past history!!!
Thanks for watching our video and sharing your thoughts. Do subscribe to our channel and stay tuned for more. Cheers!
1,2 are supervised learning. 3 is reinforcement learning in Quiz.. Video was good, understanding the concepts.. Thank you..
You are welcome
1. FB case: Supervised scenario (photo tags become labels)
2. Netflix case: Supervised scenario (like and dislike of a movie/show become the label)
3. Bank fraud case: Unsupervised scenario
Thank you for watching our video!
You guys at Simplilearn are doing great service by making these educational videos. It helps me a lot.
Hey Dipendra, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
I got impressed by this tutorial and interested to learn Machine Learning.. Can you guide me..
Machine learning is taking over the world- and with that, there is a growing need among companies for professionals to know the ins and outs of machine learning. You can start with this amazing playlist which helped a lot of people: czcams.com/video/ukzFI9rgwfU/video.html
This playlist will provide you with the solid basic knowledge of Machine learning and it types with examples. It has videos both in R and Python. If you want to go further and get certified in Machine learning, check this out: www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course.
What is the use of machine learning .iam looking for good soft ware
@@poojaritulasi7680 Hi Poojari, machine learning is used in the various fields now. We recommend you check out the below link to know about Machine Learning and why it matters a lot: www.simplilearn.com/what-is-machine-learning-and-why-it-matters-article.
Wonderful editing and we can understand easily.
Answers:
1: supervised
2: supervised
3: unsupervised
Wow! You got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Well! First of all thanks for this wonderful and informative video.
The answer to the questions in the video might be 1.supeervised 2. supervised 3 . unsupervised
Am I correct?
Wow! You got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Mudit Goyal Dumbass , 1 is supervised not supeervised
In CZcams, It can display the videos as per our frequent past search.
Exactly! Search engines work based on Machine Learning concepts. Machine learning is taking over the world- and with that, there is a growing need among companies for professionals to know the ins and outs of machine learning. You can start with this amazing playlist which helped a lot of people: czcams.com/video/ukzFI9rgwfU/video.html
This playlist will provide you with the solid basic knowledge of Machine learning and it types with examples. It has videos both in R and Python. If you want to go further and get certified in Machine learning, check this out: www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course.
Or your likes or dislikes after watching them.
Amazing video!! Thanks for sharing the knowledge.
The answers are :
1.Supervised
2.Supervised
3.Unsupervised, right?
Wow! You got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
@@SimplilearnOfficial If you use the decision tree by using existing features to classify a transaction as fraud (1) and no-fraud (0) than you are using a supervised learning based on classification. Right?
Yes, a decision tree is a supervised learning algorithm and is it used for classification problems."
I used supervised learning to decide:
1. Supervised.
2. Supervised.
3. Unsupervised.
Hi, you got everything right. Kudos!
Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious-looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
I found this machine learning series because of "Machine Learning". So thank you "Machine Learning" and of course thank you Simplilearn.
Hi Sarthak, thanks for appreciating our work and for the wonderful comment. Do subscribe to our channel to stay posted on upcoming tutorials. Cheers!
I admire your teaching skill. The reason why simplilear is the first choice of the learner.
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
It's very easy to understand how ML algorithms work. Thanks for it.
Hey Sanjeev, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
I have exam tomorrow, and this just one video boosted my confidence to write the exam well with your easy explanations...😊
Hello thank you for watching our video .We are glad that we could help you in your learning !
Amazing video. Thank you Simplilearn. Example where I see application of machine learning could be CZcams itself. Once I watch a video on cooking, all recommendations on cooking video starts popping up!
Glad you enjoyed it!
Based on ML, SimpliLearn models those videos which could cater Huge Knowledge and important numerous Subscribers😃
Thanks for watching our video. Cheers!
S1 - Supervised - the labels are the faces of friendsS2 - Supervised - the labels are based on past views and sentiments of movies watched S3 - Unsupervised - no perceived labels available; based on outliers
Wow! you got it all right. Below are the right answers and explanation for the same.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
"Hey Siri, can you remind me to book a cab at 6 pm today?"
"Here's what i found on the web for Keanu Reeves' Sixteenth Birthday"
😐
😂😂
Lol
😂😂
:)
Ha ha I think kelvin plank law...
Amazing amazing video! I have shared with many friends over WhatsApp, can't thank you enough.
Quiz answer - scenario 1 is supervised, scenario 2 is supervised, and scenario 3 is unsupervised?
Hi Pooja, thanks for your reply! We will give out the answers to the quiz on Wednesday, 26th September 2018.
Wow! You got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Thank you pooja for your answers it helped me to understand
@Simplilearn , wonderful and fantastic tutorial! It's really helpful
1,2 are supervised learning and 3 one is unsupervised
Glad it was helpful!
I have been trying to understand this concept for 3 days. Fortunately got your video and thanks for video.
Glad you enjoyed our video! We have a ton more videos like this on our channel. We hope you will join our community!
Excellent summary. I have shared this with all my linkedin connections.
Much appreciated!
In my point of view 1- Scenario will be using the reinforcement learning. the reason is in the reinforcement example which is explained based on that only i am telling.
2 - scenario will be using the supervised learning.
3 - scenario will be using the unsupervised learning.
If it's wrong please correct me.
Thanks Simplilearn
Hi Chaithanya, thanks for your reply! We will give out the answers to the quiz on Wednesday, 26th September 2018.
Thanks for replying to the quiz Chaitanya. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Thanks for your answers and correcting me where did some mistake in quiz but I learned it thank you so much simplilearn
You are very welcome Chaitanya. Do subscribe to the channel and stay tuned.
yeah wow!!! you explained so nice...😍😍
ans is 1. super
2. super
3.unsuper
am i correct???
Hi Pratibha, you got all the answers correct. Kudos.
Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
@@SimplilearnOfficial I am a massive fan of visual aids and numerous example driven content and interesting narratives in learning and kudos to SL
I love the headfirst set of books which heavily uses stories and visual aids
I have a question.I am looking to sign up for a course in AI AND ML.
My question is if lectures n SL will be heavily based on visual narrations and interesting examples throughout the course ?
IF SO,that would be truly wonderful and clutter breaking
That's great to hear it. Our courses do have visual narrations with 15+ real life industry projects. If you are interested to take up a more structured and formal course, you can find the details here: www.simplilearn.com/artificial-intelligence-introduction-for-beginners-training-course.
Respected ma'am, the video was highly informative. Thank you ma'am for teaching so many concepts about machines😄😄
Hello, thank you for watching our video. We are glad that you liked our video. Do subscribe and stay connected with us. Cheers :)
Please help me to learn more ...My Email Id is salaudeen03041969@gmail.com
..humans do learn from past experiences but that alone stifles innovation and problem solving..we are good at learning about the right now too..
Humans can do it because of our cognitive ability and sixth sense.
i understood the concept of machine learning in less than 10 mins. thank you.
Glad it helped!
Scenario-1: supervised
Scenario-2: supervised
Scenario-2: unsupervised
Am i correct,mam?
"Wow! You got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of ""fraud"" and ""not fraud"". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'."
@@SimplilearnOfficial Why is scenario 3 unsupervised learning? How does the system know that sth is "fraud" without being fed in previous cases which were called "fraud"? Like it has to know the features that make sth "fraud" before it can identify sth as "fraud"
Simplilearn 🙌🏻
what i thought too
@@angelflyinghigh1300 Hi Lucia, I would recon it (for example) compares properties of many transactions and puts the common ones in groups and thus sees which properties are anomalies (like, really big transaction amounts, or a never used bank account located far away, or many many small transactions with unclear description). But, that's just my two cents, I'm far from knowledgeable of Machine learning :)
Scenario 1 supervised
Scenario 2 reinforced
Scenario 3 unsupervised
Hi Isha, thanks for your reply! We will give out the answers to the quiz on Wednesday, 26th September 2018.
Hi Isha, you almost got everything right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
wonderful and fantastic tutorial! It's really helpful. The explanation is so clear. thumb up to the tutor.
Hi Amilcar, we are glad that you found our video helpful and informative. Thank you for your kind words. Spread the word by liking, sharing and subscribing to our channel! Cheers :).
This Knowledge will help us Forever in Life, School Rote Learning is for a Short Period of Time which cannot help us, we can just get Marks and that's all, but knowledge will be with us Forever.
True that. We hope you found our video helpful. Cheers!
I liked your video. Now youtube will recommend me your other videos without actually searching for them. This is awesome. This is Machine Learning.
Great to hear it. This playlist will provide you with the solid basic knowledge of Machine learning and it types with examples. It has videos both in R and Python. If you want to go further and get certified in Machine learning, check this out: www.simplilearn.com/big-data-and-analytics/machine-learning-certification-training-course.
You cleared my chart doubts in a single video
We are glad in clarifying your doubts. Do subscribe to our channel and do not forget to hit the bell icon for never miss another update. Cheers :)
1->supervised
2->supervised
3->unsupervised
Hi Sagar, you got everything right. Kudos!
Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious-looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Wonderful video, it's made in such a way that a layman can also understand this..thanks a ton.. please share the answer of that quiz
Hi Bhawna, we are glad that you like our videos! We will give out the answers to the quiz on Wednesday, 26th September 2018.
Here are the answers to the quiz with the explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
you Defined the besics of mechine learning a very simple way amazing video
Glad you think so!
Answers
Scenario 1 - Supervised
Scenario 2 - Supervised
Scenario 3 - Unsupervised
Please tell me if I am correct or not. Thank Simplilearn !
"Wow! You got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of ""fraud"" and ""not fraud"". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'."
Scenario-1: supervised
Scenario-2: supervised
Scenario-2: unsupervised
"Wow! You got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of ""fraud"" and ""not fraud"". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'."
Awesome, I am glad to watch this video about Machine Learning. Such a simple and clear explanation. Thank you!
Glad it was helpful!
Facebook face recognition with tagged data - Supervised learning
Movie recommendation - Unsupervised
Fraud detection - Unsupervised
Thanks for replying to the quiz, Mustafa. You almost got the right answer. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
After watching ur video I got interest in learning machine learning
Such an crystal clear explanation 🙂
Glad to hear that
Then you must download the Anaconda package and start coding
Some of the best examples are youtube,twitter,flipcart....etc., in which these kind apps extract the content for us based on our past search data and preferences
Great examples! Social medias and shopping karts show contents based on our past search data and preferences.
Thank you for such a good explanation!
Greetings! Thank you for your kind words. Spread the word by liking, sharing and subscribing to our channel! Cheers :). You can also explore our playlists for more Machine Learning Videos - czcams.com/video/ukzFI9rgwfU/video.html
1 - Unsupervised because FB checks your friends face using image recognition
2 - Supervised
3 - Unsupervised
Is this right?
Hi Anjaney, thanks for your reply! We will give out the answers to the quiz on Wednesday, 26th September 2018.
Hi Anjaney, you almost got everything right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
@@SimplilearnOfficial In scenario 3, if you say the suspicious transactions are not defined. Does that means the system might know the valid transaction.?
This means that the model will study the pattern, evaluate whether the transaction done is normal as per the customer history and hence detect a suspicious transaction.
@@SimplilearnOfficial There is a mistake on the answer, Netflix uses AutoEnconders, and it is unsupervised learning...
Facebook face recognition : supervised , netflex movie choice: reinforced , fraud detection : reinforced
Hi Sitaram, thanks for your reply! We will give out the answers to the quiz on Wednesday, 26th September 2018.
Hi Sitaram, thanks for replying to the quiz. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
@@SimplilearnOfficial thank you for the beautiful explanations!!
You are very welcome! Do subscribe to our channel and stay tuned!
@@@SimplilearnOfficial fraud transactions to be reinforcement learning right ( as it gives a negative feedback when some enters their data incorrectly )
CORTANA is learning and doing amazing job...
Of course, you are right about that!
This was very helpful, It has been hard grasping the idea we have managed to create machines, or scripts, that run mostly off of numbers and organization, to "learn"
Hello thank you for watching our video .We are glad that we could help you in your learning !
@Simplilearn Thank you for this video! Shows the power of simplicity and your ability to simplify things. And asking people to comment on the 3 scenarios, great engagement strategy! 🙂
Glad it was helpful!
Great video, very easy to understand. Thanks Simplilearn....
We are glad you found our video helpful, Maini. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
Scenario-1: supervised
Scenario-2: supervised
Scenario-2: unsupervised
Am i correct,mam?
Awesome summary. Loved it.
"Wow! You got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of ""fraud"" and ""not fraud"". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'."
Google crowdsource is the best example of machine learning to understand easily by a layman and also contribute. This will help to make better for different Google products like translate, maps, photos, searching and finding, etc.
Thanks for watching our video and sharing your knowledge. Cheers!
examples of machine learning: weather prediction, prediction of natural events, share price prediction, recommendation system etc.
You are right about the examples. Nice thought!
Scenario 1 - Supervised Learning,
Scenario 2 - Reinforcement Learning,
Scenario 3 - UnSupervised Learning
Hi Neha, Below are the right answers and explanation for the quiz.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'
A great gratitude towards simplilearn...really informative video...☺
Hey Manasi, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
The video was quite interesting and informative. I would like to be your part of learning ML.
Hi Mainak, we are glad you found our video helpful and informative. Do show your love by subscribing our channel using this link: czcams.com/users/Simplilearn and don't forget to hit the like button as well. Cheers!
You can train your machine learning model for image classification even without writing any code in an Android app called Pocket AutoML. It trains a model right on your phone without sending your photos to some "cloud" so it can even work offline.
Keep learning with us .Stay connected with our channel and team :) . Do subscribe the channel for more updates : )
Thanks for the amazing video,I think the ans is-
1.Supervised Learning
2.Supervised Learning
3.Unsupervised Learning
Hi Soumyadeep, you got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
these examples are so helpful, thanks for making this video! YOU ROCK!
Hi Victoria, we are glad you found our video helpful. Do subscribe to our channel and get our new video updates directly into your email. If you have any questions related to these videos, you can post in the comments section, we will clear your queries/doubts.
The video was quite interesting and informative. I would like to be your part of learning ML.
It's very easy to understand how ML algorithms work. Thanks for it.
Hey Natalie, thank you for appreciating our work. We are glad to have helped. Do check out our other tutorial videos and subscribe to us to stay connected. Cheers :)
I recently join your team,because i lovet it.
Excellent work
WoW! we are glad you joined our community. Thanks for your love and support!
sc 1 - UNs 2 - Supervised, 3 - SUpervised
Keep learning with us .Stay connected with our channel and team :) . Do subscribe the channel for more updates : )
K-nearest neighbors algorithm example really opened my mind to understand how it works
Simple and very easy to understand 👍
Glad to hear that
CZcams recommends and shows the type of videos based on which we watched before.Which type of learning is happening here?Can anyone explain?
Deep Neural network concepts have been implemented for CZcams recommendation. For more detailed explanation, go through this blog: towardsdatascience.com/how-youtube-recommends-videos-b6e003a5ab2f
1.supervised
2.reinforcement
3.unsupervised
Hi Karthik, thanks for your reply! We will give out the answers to the quiz on Wednesday, 26th September 2018.
Hi Karthick, thanks for your reply to the quiz. You are almost right about everything and here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud".
The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
@@SimplilearnOfficial hey tx for reply. But I was in little bit confused regarding the second scenario. .tx for nice explanation. ..hope for the more best quizs and tutorials too
Thanks, Karthik. We are coming up with more new things in the future. So do subscribe to our channel and stay tuned.
@@SimplilearnOfficial I subscribed long back. .i just love your channel
Thanks for explaining the basics of machine learning.
You are welcome!
Awesome video !
Answers for quiz:
1. Supervised
2. Unsupervised
3. Supervised
Hi Harry, thanks for your reply! We will give out the answers to the quiz on Wednesday, 26th September 2018.
Hi Harry, thanks for replying to the quiz. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
To me the 3 scenarios looks like
1. Supervised
2. Supervised
3. Unsupervised
Hi Nitesh, you got everything right. Kudos!
Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Why sir scenario one has supervised lwarning
Hi Onkar,
Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labeled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious-looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
And if photo is not tagged ..?
It will come under unsupervised learning.
Amazing video! I was getting headache learning the same topic from a coding site, I guess there is more than one ways if understanding things. Thank you!
Glad you liked it!
Thank you for such great video. I hope my all concepts will be cleared through this sessions🙌
We are glad you found our video helpful, Sakshi. Like and share our video with your peers and also do not forget to subscribe to our channel for not missing video updates. We will be coming up with more such videos. Cheers!
Scenario 1: Supervised Learning
Scenario 2: Reinforcement Learning
Scenario 3: Unsupervised Learning
Keep learning with us .Stay connected with our channel and team :) . Do subscribe the channel for more updates : )
A day before exam and this video really helped with the concepts and queries, thanks!
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
Umm 1st is supervised, 2nd also supervised, 3rd is unsupervised. Am i correct?
Great video though, loved it!!
Hi Apeksha, thanks for your reply! We will give out the answers to the quiz on Wednesday, 26th September 2018.
Wow! You got all the answers right. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Scenario 1 is supervised earning because machine know the data(both friend photo and their name).
2. Netflix is same as person identify song (high intensity high tempo )
3. Fraud is unsupervised I guess.
By the way video is good. It's wow in one word
Hi Amogha, you are absolutely right about your answer and explanation. We really appreciate your kind comment. Do show your love by subscribing our channel using this link: czcams.com/users/Simplilearn and don't forget to hit the like button as well. Cheers!
@@SimplilearnOfficial Hi a quick question, should the 3rd one be case of reinforcement learning because transactions are very important and there needs to be a feedback mechanism to recorrect if there is a false positive or false negative ?
Truly a REMARKABLE explanation. Can you do a video about active learning too?
Great suggestion! We will share it with our team.
We can analyse the comments like machine learning to find answers 😁😁
You got it, what is machine learning hahaha.
Lol...
1 supervised learning
2 supervised learning
3 unsupervised learning
I appreciate how you teach with examples
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
Great teacher. Great teaching skills. Try to add quiz question after explaining a concept on your upcoming videos, it really helps us to test our understanding on that topic. By d way great explanation =.
Thank you for the appreciation. You can check our videos related to various technologies and subscribe to our channel to stay updated with all the trending technologies.
CZcams itself a best example.. is it not? Unsupervised learning... Sometimes reinforce
You are so right about it!
Scenario-1: supervised learning
Scenario-2: supervised
Thanks for replying to the quiz Chaitanya. Here are the answers with explanation.
Scenario 1: Facebook recognizes your friend in a picture from an album of tagged photographs
Explanation: It is supervised learning. Here Facebook is using tagged photos to recognize the person. Therefore, the tagged photos become the labels of the pictures and we know that when the machine is learning from labelled data, it is supervised learning.
Scenario 2: Recommending new songs based on someone’s past music choices
Explanation: It is supervised learning. The model is training a classifier on pre-existing labels (genres of songs).
This is what Netflix, Pandora, and Spotify do all the time, they collect the songs/movies that you like already, evaluate the features based on your likes/dislikes and then recommend new movies/songs based on similar features.
Scenario 3: Analyze bank data for suspicious looking transactions and flag the fraud transactions
Explanation: It is unsupervised learning. In this case, the suspicious transactions are not defined, hence there are no labels of "fraud" and "not fraud". The model tries to identify outliers by looking at anomalous transactions and flags them as 'fraud'.
Hello Simplilearn , Im 9 yrs old and very interested in machine learning. This video is very cool.
Glad you liked it! We have a ton more videos like this on our channel. We hope you will join our community!