Coding Lane
Coding Lane
  • 55
  • 2 214 285
Gated Recurrent Unit | GRU | Explained in detail
Gated Recurrent Unit (GRU) is a type of Recurrent Neural Network (RNN) which performs better than Simple RNN while dealing with longer input data. Gated Recurrent Unit (GRU) is an advance RNN which can retain some valuable information for a longer period of time without updating it. The memory context of GRU has both long term and short term memory combined. The update gate in GRU helps to retain a valuable context as long as it is needed. The reset gate in GRU helps to forget any context when not needed, allowing more room for new information to come in.
Gated Recurrent Unit (GRU) is used in many real-world applications. The video gives a detailed explanation of Gated Recurrent Unit (GRU) through which you will understand the working of it and equations through which it operates.
➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Timestamps:
0:00 Intro
0:24 RNN limitations
3:38 LSTM vs GRU
4:42 GRU explained
9:13 Update Gate
10:45 Reset Gate
13:09 Summary
➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Follow my entire playlist on Recurrent Neural Network (RNN) :
📕 RNN Playlist: czcams.com/video/lWPkNkShNbo/video.html
➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖
✔ CNN Playlist: czcams.com/video/E5Z7FQp7AQQ/video.html
✔ Complete Neural Network: czcams.com/video/mlk0rddP3L4/video.html
✔ Complete Logistic Regression Playlist: czcams.com/video/U1omz0B9FTw/video.html
✔ Complete Linear Regression Playlist: czcams.com/video/nwD5U2WxTdk/video.html
➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖
If you want to ride on the Lane of Machine Learning, then Subscribe ▶ to my channel here: czcams.com/channels/JFAF6IsaMkzHBDdfriY-yQ.html
zhlédnutí: 124

Video

Deep Neural Network Python from scratch | L layer Model | No Tensorflow51:35Deep Neural Network Python from scratch | L layer Model | No Tensorflow
Deep Neural Network Python from scratch | L layer Model | No Tensorflow
zhlédnutí 11KPřed rokem
We will create a Deep Neural Network python from scratch. We are not going to use Tensorflow or any built-in model to write the code, but it's entirely from scratch in python. We will code Deep Neural Network with L layers in python from scratch. This video is for those enthusiasts who love to know under-the-hood details behind how things work. You can directly use the TensorFlow model to creat...
Facial Landmark Detection | OpenCV | Python | Mediapipe17:19Facial Landmark Detection | OpenCV | Python | Mediapipe
Facial Landmark Detection | OpenCV | Python | Mediapipe
zhlédnutí 9KPřed rokem
Let's make a real-time Facial Landmark Detection using OpenCV, Python, and Mediapipe API. It detects 468 facial landmarks in real time. Facial Landmark Detection is used for AR (Augmented Reality) applications. Like putting a mask, specs, or a filter on your face. Mediapipe has a bunch of solutions that help us detect facial landmarks, iris, hands, pose, and full body movement. Mediapipe offers...
Emoji Prediction | LSTM in Tensorflow | Implementation27:51Emoji Prediction | LSTM in Tensorflow | Implementation
Emoji Prediction | LSTM in Tensorflow | Implementation
zhlédnutí 8KPřed 2 lety
Do you struggle finding the right emoji at right time? Why don't we make an ML model to suggest us the emoji while typing? In this video, we will make Emoji Prediction in Tensorflow. The main aim of this video, is help you understand how to use LSTM in Tensorflow and also to use Word Embeddings. This video will teach you implementing LSTM in Tensorflow, RNN in Tensorflow, and Word Embeddings in...
Part 2 | Python | Training Word Embeddings | Word2Vec |24:28Part 2 | Python | Training Word Embeddings | Word2Vec |
Part 2 | Python | Training Word Embeddings | Word2Vec |
zhlédnutí 10KPřed 2 lety
In this video, we will about training word embeddings by writing a python code. So we will write a python code to train word embeddings. To train word embeddings, we need to solve a fake problem. This problem is something that we do not care about. What we care about is the weights that are obtained after training the model. These weights are extracted and they act as word embeddings. This is p...
Part 1 | Training Word Embeddings | Word2Vec9:38Part 1 | Training Word Embeddings | Word2Vec
Part 1 | Training Word Embeddings | Word2Vec
zhlédnutí 11KPřed 2 lety
In this video, we will learn about training word embeddings. To train word embeddings, we need to solve a fake problem. This problem is something that we do not care about. What we care about are the weights that are obtained after training the model. These weights are extracted and they act as word embeddings. This is part 1/2 for training word embeddings. In this part, we only understand the ...
Word Embedding Python | RNN | Detailed Explanation10:09Word Embedding Python | RNN | Detailed Explanation
Word Embedding Python | RNN | Detailed Explanation
zhlédnutí 9KPřed 2 lety
Word Embedding (Python) is a technique to convert words into a vector representation. Computers cannot directly understand words/text as they only deal with numbers. So we need to convert words into numbers. In this video, we have discussed what Words Embedding is and what its uses are. Word Embedding is a powerful way to make computers understand the context behind the words. With the help of ...
LSTM Recurrent Neural Network (RNN) | Explained in Detail19:32LSTM Recurrent Neural Network (RNN) | Explained in Detail
LSTM Recurrent Neural Network (RNN) | Explained in Detail
zhlédnutí 54KPřed 2 lety
LSTM Recurrent Neural Network is a special version of the RNN model. It stands for Long Short-Term Memory. The simple RNN has a problem that it cannot remember the context in a long sentence because it quickly loses information. And that is why Simple RNN has an only short-term memory. LSTM has both long-term and short-term memory. It can store any contextual information for a long time. LSTM h...
Backpropagation in RNN | Backpropagation through time8:50Backpropagation in RNN | Backpropagation through time
Backpropagation in RNN | Backpropagation through time
zhlédnutí 27KPřed 2 lety
In this video, we will understand Backpropagation in RNN. It is also called Backpropagation through time, as here we are backpropagating through time. Understanding Backpropagation in RNN helps us to know how Recurrent Neural Networks work. Also, It is important to understand the vanishing gradient problem that occurs in RNN. We will look at the general equation for computing Backpropagation in...
RNN Model Details | Recurrent Neural Networks | Deep Learning8:33RNN Model Details | Recurrent Neural Networks | Deep Learning
RNN Model Details | Recurrent Neural Networks | Deep Learning
zhlédnutí 27KPřed 2 lety
In this video, we will look at the details of the RNN Model. We will see the mathematical equations for the RNN model, and understand how one RNN Cell looks like. Recurrent Neural Network (RNN) in Deep Learning is a model that is used for Natural Language Processing tasks. It can be used to create applications like chat-bot, virtual assistants, speech-to-text, or text-to-speech. In a Recurrent ...
Types of Recurrent Neural Networks (RNNs)5:35Types of Recurrent Neural Networks (RNNs)
Types of Recurrent Neural Networks (RNNs)
zhlédnutí 28KPřed 2 lety
In this video, we will look at different types of Recurrent Neural Networks. There are mainly 3 types of Recurrent Neural Networks. 1) many-to-one 2) one-to-many 3) many-to-many The type of Recurrent Neural Network (RNN) is based on the input and output size. In the video, we also saw different types of applications that can be made using different types of Recurrent Neural Networks. ➖➖➖➖➖➖➖➖➖➖...
What is Recurrent Neural Network in Deep Learning? | RNN7:09What is Recurrent Neural Network in Deep Learning? | RNN
What is Recurrent Neural Network in Deep Learning? | RNN
zhlédnutí 58KPřed 2 lety
in this video, we will understand what is Recurrent Neural Network in Deep Learning. Recurrent Neural Network in Deep Learning is a model that is used for Natural Language Processing tasks. It can be used to create applications like chat-bot, virtual assistant, speech-to-text or text-to-speech. The word Recurrent means "occurring repeatedly". This means that the Neural Network occurs repeatedly...
Image Classification using CNN Keras | Full implementation17:56Image Classification using CNN Keras | Full implementation
Image Classification using CNN Keras | Full implementation
zhlédnutí 164KPřed 2 lety
In this video, we will implement Image Classification using CNN Keras. We will build a Cat or Dog Classification model using CNN Keras. Keras is a free and open-source high-level API used for neural networks. Building a Deep Learning model in Keras is fast and easy. I already covered the full detailed mathematical theory behind the Convolutional Neural Network (CNN). If you haven't checked that...
What is Keras and Tensorflow | Keras vs Tensorflow3:41What is Keras and Tensorflow | Keras vs Tensorflow
What is Keras and Tensorflow | Keras vs Tensorflow
zhlédnutí 19KPřed 2 lety
In this video, we will understand what is Keras and Tensorflow. Tensorflow is a free and open-source library for machine learning and artificial intelligence. It was developed by Google. And it can be used for developing large-scale machine learning applications, and it is also highly used by researchers to push the state of the art in machine learning. Keras is also an open-source library for ...
Why use Tensorflow? Explaining Tensorflow and why to use it7:20Why use Tensorflow? Explaining Tensorflow and why to use it
Why use Tensorflow? Explaining Tensorflow and why to use it
zhlédnutí 15KPřed 2 lety
Why use Tensorflow? Good question! Let's have a look at its answer in this video. Tensorflow is a free and open-source library for machine learning and artificial intelligence. It was developed by Google. And it can be used for developing large-scale machine learning applications, and it is also highly used by researchers to push the state of the art in machine learning. Tensorflow is the most ...
Backpropagation in CNN - PART 219:31Backpropagation in CNN - PART 2
Backpropagation in CNN - PART 2
zhlédnutí 25KPřed 2 lety
Backpropagation in CNN - PART 2
Backpropagation in CNN - Part 120:03Backpropagation in CNN - Part 1
Backpropagation in CNN - Part 1
zhlédnutí 50KPřed 2 lety
Backpropagation in CNN - Part 1
CNN architecture | Explaining the Architecture of CNN12:30CNN architecture | Explaining the Architecture of CNN
CNN architecture | Explaining the Architecture of CNN
zhlédnutí 93KPřed 2 lety
CNN architecture | Explaining the Architecture of CNN
Fully Connected Layer in CNN4:30Fully Connected Layer in CNN
Fully Connected Layer in CNN
zhlédnutí 71KPřed 2 lety
Fully Connected Layer in CNN
Max Pooling in Convolutional Neural Network7:36Max Pooling in Convolutional Neural Network
Max Pooling in Convolutional Neural Network
zhlédnutí 60KPřed 2 lety
Max Pooling in Convolutional Neural Network
Stride in Convolutional Neural Network (CNN)3:45Stride in Convolutional Neural Network (CNN)
Stride in Convolutional Neural Network (CNN)
zhlédnutí 68KPřed 2 lety
Stride in Convolutional Neural Network (CNN)
Padding in Convolutional Neural Network4:10Padding in Convolutional Neural Network
Padding in Convolutional Neural Network
zhlédnutí 66KPřed 2 lety
Padding in Convolutional Neural Network
Convolution Operation in CNN10:58Convolution Operation in CNN
Convolution Operation in CNN
zhlédnutí 97KPřed 2 lety
Convolution Operation in CNN
What is CNN in deep learning? Convolutional Neural Network Explained6:05What is CNN in deep learning? Convolutional Neural Network Explained
What is CNN in deep learning? Convolutional Neural Network Explained
zhlédnutí 146KPřed 2 lety
What is CNN in deep learning? Convolutional Neural Network Explained
Optimization in Deep Learning | All Major Optimizers Explained in Detail18:49Optimization in Deep Learning | All Major Optimizers Explained in Detail
Optimization in Deep Learning | All Major Optimizers Explained in Detail
zhlédnutí 20KPřed 2 lety
Optimization in Deep Learning | All Major Optimizers Explained in Detail
Adam Optimizer Explained in Detail | Deep Learning5:05Adam Optimizer Explained in Detail | Deep Learning
Adam Optimizer Explained in Detail | Deep Learning
zhlédnutí 47KPřed 2 lety
Adam Optimizer Explained in Detail | Deep Learning
RMSprop Optimizer Explained in Detail | Deep Learning6:11RMSprop Optimizer Explained in Detail | Deep Learning
RMSprop Optimizer Explained in Detail | Deep Learning
zhlédnutí 20KPřed 2 lety
RMSprop Optimizer Explained in Detail | Deep Learning
Momentum Optimizer in Deep Learning | Explained in Detail11:17Momentum Optimizer in Deep Learning | Explained in Detail
Momentum Optimizer in Deep Learning | Explained in Detail
zhlédnutí 23KPřed 2 lety
Momentum Optimizer in Deep Learning | Explained in Detail
Exponentially Weighted Moving Average or Exponential Weighted Average | Deep Learning9:09Exponentially Weighted Moving Average or Exponential Weighted Average | Deep Learning
Exponentially Weighted Moving Average or Exponential Weighted Average | Deep Learning
zhlédnutí 13KPřed 2 lety
Exponentially Weighted Moving Average or Exponential Weighted Average | Deep Learning
Mini Batch Gradient Descent | Deep Learning | with Stochastic Gradient Descent8:04Mini Batch Gradient Descent | Deep Learning | with Stochastic Gradient Descent
Mini Batch Gradient Descent | Deep Learning | with Stochastic Gradient Descent
zhlédnutí 17KPřed 2 lety
Mini Batch Gradient Descent | Deep Learning | with Stochastic Gradient Descent

Komentáře

  • @AshwinMaccount
    @AshwinMaccount Před 5 hodinami

    we missed u so much bro. Now you're back , please dont stop making these content. It will be so much helpful to me. I've watched all your previous videos. I learnt deep learning from your videos only bro.

  • @Ramu9119
    @Ramu9119 Před 7 hodinami

    thanks for the video champ

  • @chakri6262
    @chakri6262 Před 13 hodinami

    keep doing these videos upto transformers bro. It is very helpful. Great work

  • @Aditya-ri7em
    @Aditya-ri7em Před dnem

    bro i just conmpleted your cnn playlist , You did a great job in it man

  • @dheemanth_bhat
    @dheemanth_bhat Před dnem

    awsm bro u r bak... thanks for bringing back ur valuable content

    • @CodingLane
      @CodingLane Před dnem

      Hey thanks a lot for keeping me motivated. Really appreciate 😄

  • @mr.unknown6179
    @mr.unknown6179 Před dnem

    If possible please share your social media username

  • @mr.unknown6179
    @mr.unknown6179 Před dnem

    Thanks bro for all the videos.

  • @simranm.552
    @simranm.552 Před dnem

    Thank you:)

  • @user-xx4sl1qk1o
    @user-xx4sl1qk1o Před dnem

    genius genius broooooooooo

  • @suhaibfarooq8253
    @suhaibfarooq8253 Před dnem

    Very good explanation

  • @JagTheRipper
    @JagTheRipper Před dnem

    Just to check at 18:07, would dZ1 not be n1Xn1 and X^T be mXn0 for the shapes, based on your explanation and workings? How would the dot product of both work in this case?

  • @JagTheRipper
    @JagTheRipper Před 2 dny

    Hey man, just wanted to say, just found your channel, thanks for uploading these videos, great stuff, great content for beginners in learning Neural Networks. Appreciate your content on how you delve into the mathematical breakdown of the differentiation part as well. Well done, keep it up :)

  • @sampathcse16
    @sampathcse16 Před 3 dny

    Super good explanation. Very indepth insights given. Thank you for taking time and explaining it

  • @ArchitStark
    @ArchitStark Před 3 dny

    Can you change the order of the video in playlist, the LSTM comes first and backpropogation comes next, but LSTM video requires one to see the Backpropogation video first

  • @HusnainTalib-r5c
    @HusnainTalib-r5c Před 7 dny

    you deserve a like.

  • @ankitprakash7949
    @ankitprakash7949 Před 8 dny

    just completed watching all your videos and what I feel sad about is that you are inactive since 2 years. I just want to ask is everything alright because you suddenly disappeared from CZcams. If everything is okay then please continue with your channel as I totally love your videos and teaching style

  • @hamza09100
    @hamza09100 Před 8 dny

    hello , I believe that sigma goes from zero to m not from 1 to m , anyway thanks for the great explanation

  • @inhibited44
    @inhibited44 Před 9 dny

    When I took regression analysis years ago, there was a way to look at residuals and outliers to see if the data might not look right for certain observations. Does deep learning have that way to inspect images to see if some don't look good enough?

  • @mukeshgupta9806
    @mukeshgupta9806 Před 13 dny

    By implementing the same code it is showing an error: weight is not defined what should I do

  • @omoniyitope7826
    @omoniyitope7826 Před 13 dny

    This is really interesting and simplified. Thank you so much for the handwork you put in

  • @DilpreetKaur-zq8je
    @DilpreetKaur-zq8je Před 14 dny

    Thnk you very much sir ❤.You helped me a lot.

  • @tarunicab7376
    @tarunicab7376 Před 15 dny

    It is showing can't import sequential from tensorflow. model how to fix this error

  • @user-ry3tu1hx7h
    @user-ry3tu1hx7h Před 16 dny

    while loading the dataset i get an error msg

  • @reenus134
    @reenus134 Před 17 dny

    Love your explanation

  • @lazyraconteur8279
    @lazyraconteur8279 Před 17 dny

    At 14:40 why are we multiplying with (1/m), even though it is not mentioned in the formula?

  • @vijayadurgakavya9178
    @vijayadurgakavya9178 Před 20 dny

    Thank you man please keep doing these kind of videos

  • @user-gf2hp2ij4x
    @user-gf2hp2ij4x Před 20 dny

    Underrated channel fr

  • @ks3356
    @ks3356 Před 20 dny

    Wonderfully explained. Just finished watching all the 12 videos from your playlist.....

  • @ernestmodise4953
    @ernestmodise4953 Před 21 dnem

    Hi Jay "Don't laugh at me, I have always been programing of a external compiler (Java / Matlab) - After launching your github template, the jupyter blank code is not in edit mode, what must I do

  • @unnimk75
    @unnimk75 Před 24 dny

    Wonderful explanation.

  • @PunnanaVinayAnjanch21b076
    @PunnanaVinayAnjanch21b076 Před 25 dny

    for simplicity how can partial differentiation of L/Z3 be equal to the difference of Z3 , please kindly explain this🙏 @coding lane ??

  • @abcdedcba561
    @abcdedcba561 Před 25 dny

    When creating the bigrams (for each of two adjacent words), the order should matter. But why you insert all the possible combinations in the bigrams list? I think the order of the words as it appear in the corpus is important to capture the relationship between adjacent words.

  • @amlanbdey
    @amlanbdey Před 26 dny

    How the sum over m (number of onsevation) gets included by the matrix multiplication of the matrices that are made of one state's variable. A2,A3, Y etc all are matrices of just one snapshot or just one state of the neural network.

  • @franzkingstein2686
    @franzkingstein2686 Před 27 dny

    Bro you are great. Respect ++

  • @myquestforknowledge
    @myquestforknowledge Před 27 dny

    nice explanation. CNN layers do complex jobs of finding edges through filters. So CNN + flatten layer + ANN gives output.

  • @ashutoshpatidar3288
    @ashutoshpatidar3288 Před 27 dny

    bro can you plese tell, what resources do you follow for learning and such indepth understanding of this concepts?

  • @vg5675
    @vg5675 Před 27 dny

    how to select best features to get the highest possible f1 score

  • @cihadozdemir9124
    @cihadozdemir9124 Před 27 dny

    thank you very much

  • @garimakaushik4744
    @garimakaushik4744 Před 28 dny

    great help. Thanks for all the videos. too good

  • @creepsow1236
    @creepsow1236 Před měsícem

    very nice aaa frr

  • @anilsaroj3390
    @anilsaroj3390 Před měsícem

    @codeboosterjp Could you please share your ppt?

  • @areenanshumanprusty7809
    @areenanshumanprusty7809 Před měsícem

    Isn't axis=1 row wise summation ?

  • @SafetyLaunda
    @SafetyLaunda Před měsícem

    When finding del(Cost)/del(Bias), is it really column wise summation instead of row wise summation because we are reducing rectangular matrix of n3*m to n3*1 vector? I might be wrong, but I think there is a mistake

  • @CrashBandicoot-qp8vq
    @CrashBandicoot-qp8vq Před měsícem

    can you please reference the values of beta1 and beta2 and epsilon ?

  • @Sansaar_Ek_Vistaar
    @Sansaar_Ek_Vistaar Před měsícem

    The best ever explanation with detailed mathematical explanation

  • @drelijahmikail3916
    @drelijahmikail3916 Před měsícem

    why 2m specifically? There are differences of 2m points, but there are only m values.

  • @algorithmo134
    @algorithmo134 Před měsícem

    Hi @Coding Lane, I dont get the part at 7:05 dL/df. Can you explain where did f2'(Z2) go?

  • @algorithmo134
    @algorithmo134 Před měsícem

    You made a small mistake while typing the code for derivative_tanh(x) function. ✔ The correct code will be : def derivative_tanh(x): return 1 - np.power(np.tanh(x), 2)

  • @NkembehBenjaminSCC
    @NkembehBenjaminSCC Před měsícem

    thanks i really enjoy the playlist

  • @algorithmo134
    @algorithmo134 Před měsícem

    At 8:00, Is there a mistake? You should take partial derivative with respect to a?