![LiveLessons](/img/default-banner.jpg)
- 323
- 2 948 273
LiveLessons
Registrace 7. 06. 2007
"LiveLessons is the leading video training library for IT, creative, & business professionals - from Pearson, the leading learning company. LiveLessons brings the world’s leading authors, trainers, and experts directly to you in video. Learn the skills you need to succeed with thousands of hours of video courses led by bestselling authors published by Addison-Wesley, Prentice Hall, Cisco Press, Pearson IT Certification, Sams, VMware Press, and Que. The LiveLessons channel features a selection of free video tutorials extracted from the full video training courses.
Audiences Served: IT Certification Candidates, Programmers & Developers, IT Managers, System Administrators, Business Professionals, Personal Technology
Learn More: www.informit.com/video
Sign up to hear from us, including information about video course sales, at informit.com/newsletters.
Audiences Served: IT Certification Candidates, Programmers & Developers, IT Managers, System Administrators, Business Professionals, Personal Technology
Learn More: www.informit.com/video
Sign up to hear from us, including information about video course sales, at informit.com/newsletters.
Big O Notation with Jon Krohn
Chief Data Scientist Jon Krohn discusses big O notation, a fundamental computer science concept that is a prerequisite for understanding almost everything else in data structures, algorithms, and Machine Learning optimization.
Explore three of the most common big O runtimes, constant, linear, and polynomial. The lesson wraps up with an overview of the other common runtimes and performance variation.
This lesson is an excerpt from “Data Structures, Algorithms, and Machine Learning Optimization LiveLessons.” Purchase the entire video course at informit.com/youtube and save 50% with discount code CZcams.
Also available in O’Reilly Online Learning (Safari) subscription service.
Explore three of the most common big O runtimes, constant, linear, and polynomial. The lesson wraps up with an overview of the other common runtimes and performance variation.
This lesson is an excerpt from “Data Structures, Algorithms, and Machine Learning Optimization LiveLessons.” Purchase the entire video course at informit.com/youtube and save 50% with discount code CZcams.
Also available in O’Reilly Online Learning (Safari) subscription service.
zhlédnutí: 1 986
Video
Regression with Machine Learning with Jon Krohn
zhlédnutí 2,3KPřed 3 lety
Jon Krohn provides practical real-world demonstrations of regression, a powerful, highly extensible approach to making predictions. He distinguishes independent from dependent variables and discusses linear regression to predict continuous variables, first with a single model feature, and then with many including discrete features. He completes the lesson with logistic regression for predicting...
Gradients in Machine Learning with Jon Krohn
zhlédnutí 1,4KPřed 3 lety
The gradient captures the partial derivative of cost with respect to all of our machine learning model's parameters. To come to grips with it, Jon Krohn carries out a regression on individual data points and derives the partial derivatives of quadratic cost. He then gets into what it means to descend the gradient and derives the partial derivatives of mean squared error, enabling you to learn f...
Eigenvectors and Eigenvalues with Jon Krohn
zhlédnutí 3,1KPřed 3 lety
Data scientist Jon Krohn introduces the linear algebra concepts of Eigenvectors and Eigenvalues with a focus on Machine Learning and Python programming. This lesson is an excerpt from “Linear Algebra for Machine Learning LiveLessons” Purchase the entire video course at informit.com/youtube and save 50% with discount code CZcams. Also available in O’Reilly Online Learning (Safari) subscription s...
Working with While Loops in Python
zhlédnutí 451Před 4 lety
Arianne Dee demonstrates how "while loops" work in the Python programming language. This lesson is an excerpt from Introduction to Python LiveLessons. Purchase the entire course at informit.com/youtube and save 50% with discount code CZcams. Also available in O’Reilly Online Learning (Safari) subscription service.
Write a MadLibs Program in Python
zhlédnutí 14KPřed 4 lety
Arianne Dee demonstrates how to start programming with Python by walking you through building a MadLibs program. This lesson is an excerpt from "Introduction to Python LiveLessons." Purchase the entire course at informit.com/youtube and save 50% with discount code CZcams. Also available in O’Reilly Online Learning (Safari) subscription service.
What is Programming?
zhlédnutí 2,7KPřed 4 lety
Arianne Dee provides a high level view of the programming world. This lesson is an excerpt from Introduction to Python: Learn How to Program Today with Python. Purchase the entire course at informit.com/youtube and save 50% with discount code CZcams. Also available in O’Reilly Online Learning (Safari) subscription service.
Convolutional Neural Networks for Machine Vision with Jon Krohn
zhlédnutí 2,4KPřed 4 lety
Jon Krohn introduces convolutional layers, which are used to build ConvNets in TensorFlow. He then covers the gamut of machine vision applications including residual networks, image segmentation, object detection, transfer learning, and capsule networks. This lesson is an excerpt from Machine Vision, GANs, and Deep "Reinforcement Learning LiveLessons, 2nd Edition." Purchase entire course at inf...
How Deep Learning Works with Jon Krohn
zhlédnutí 9KPřed 4 lety
Jon Krohn dissects what artificial neurons are and demonstrates how to link them together to be a neural network. He then uncovers how neural networks learn from data and walks you through building an intermediate complex network in TensorFlow to tackle a Machine Vision problem. This lesson is an excerpt from "Deep Learning with Tensorflow, Keras and PyTorch LiveLessons, Second Edition." Purcha...
Deep Learning for Natural Language Processing with Jon Krohn
zhlédnutí 2,4KPřed 4 lety
Jon Krohn introduces how to preprocess natural language data. He then uses hands-on code demos to build deep learning networks that make predictions using those data. This lesson is an excerpt from "Deep Learning for Natural Language Processing LiveLessons, 2nd Edition." Purchase entire course at informit.com/youtube and save 50% with discount code CZcams code. Also available in O’Reilly Online...
Uncle Bob on Clean Agile the Book: Taking it Back to the Basics
zhlédnutí 8KPřed 4 lety
Robert C. Martin (Uncle Bob) reintroduces Agile values and principles for a new generation of programmers and nonprogrammers alike, striping away misunderstandings and distractions that over the years made using Agile difficult. This video from Uncle Bob explains why he wrote the book Clean Agile: Back to Basics. Purchase the book at informit.com/cleancode. The book is also available at all maj...
How to Define and Use Operator Overloads in Kotlin
zhlédnutí 499Před 5 lety
Java champion Justin Lee demonstrates how to define and use Kotlin operator overloads. This lesson is an excerpt from the video course "Kotlin from the Ground Up." Purchase the full course and save 50% with discount code CZcams at informit.com/youtube. Also available in O'Reilly (Safari) Online Learning subscription.
Use Destructuring in Kotlin
zhlédnutí 277Před 5 lety
Java champion Justin Lee demonstrates how to use destructuring to unpack a class instance into separate variables. This lesson is an excerpt from the video course "Kotlin from the Ground Up." Purchase the full course and save 50% with discount code CZcams at informit.com/youtube. O'Reilly (Safari) Online Learning subscribers - you can access the complete course at learning.oreilly.com/videos/ko...
Run Jupyter Notebooks in the Cloud with Azure
zhlédnutí 9KPřed 5 lety
Juptyer team member Jamie Whitacre shows you how to run Jupyter Notebooks in the Cloud with Azure Notebooks (and you don't have to download anything). This lesson is an excerpt from the video course Using Jupyter Notebooks for Data Science Analysis in Python LiveLessons. Purchase the full course at informit.com/youtube and save 50% with code CZcams. Also available in O'Reilly Online Learning (S...
Create Presentation Slides from Jupyter
zhlédnutí 51KPřed 5 lety
Jamie Whitacre demonstrates how to create dynamic presentation slides from your Jupyter Notebook using RISE (Reveal js Jupyter/IPython Slideshow Extension). This lesson is an excerpt from the video course Using Jupyter Notebooks for Data Science Analysis in Python LiveLessons. Purchase the full course at informit.com/youtube and save 50% with code CZcams. Also available in O'Reilly Online Learn...
How Does Blockchain Transform Businesses and Drive Growth?
zhlédnutí 396Před 5 lety
How Does Blockchain Transform Businesses and Drive Growth?
Java Platform Module System Basic Concepts
zhlédnutí 646Před 5 lety
Java Platform Module System Basic Concepts
Working with Numeric Data Types in Java
zhlédnutí 384Před 5 lety
Working with Numeric Data Types in Java
Working with Predefined Classes in Java
zhlédnutí 1,2KPřed 5 lety
Working with Predefined Classes in Java
A Model for Activating Change in your Organization - Assessment Phase
zhlédnutí 63Před 5 lety
A Model for Activating Change in your Organization - Assessment Phase
How to Go from an OO Design Pattern to a Functional Foundation
zhlédnutí 370Před 5 lety
How to Go from an OO Design Pattern to a Functional Foundation
Thanks for the Nice Video
How is it useful?
The second chapter's title should be "Cart Pole", not "Cart Pool"!
This is one of the best tutorial for DQN. Thanks a lot man
this guys talks way to fast
When I run your notebook on my machine the training time is so much slower! You are able to do 1000 episodes in <30 seconds in the video but on my own machine it takes more like 45 minutes! Do you know what could cause this massive increase in runtime?
In this video Jon mentions a previous video where neural networks are already introduced. Where is that video? Cannot find it in this playlist since current video seems to be the first one in this playlist?
how to download the slides?
How do you select the pivot of rotation
1:04:10 We are still performing gradient descent, rather than gradient ascent, because we're using the Mean Squared Error loss function, between a target q-value prediction, and our current q-value prediction. Therefore the further away we are from this target, the larger the Mean Squared Error, and that distance is what the stochastic gradient descent is minimising.
After watching this video it seems like I have been taught RL by Johnny Sinns😂
Thank you for these great lessons!
Thankyou , I almost gave up trying to understand this. Big thanks
gold
Loving your Mathematical Foundation series on Udemy right now. Planning to hit up O'Reilly as soon as I finish these so I can continue with your curriculum.
Thank you for this excellent tutorial! Better than several others I watched and didn't find as helpful. The way you built things up theoretically and in code was extremely well organized, well explained, and easy to follow. Much appreciated!
Day saver! Thanks a lot.
Very nice explanation, thank you very much
Best explaination, after seeing so many channels videos 🙏
I read it. It has REALLY good advice. Half of it is just filler though; Uncle Bob's flavour of Agile is simple enough to be explained in 50-60 pages, so there's a bunch of extra unnecessary stuff there, even for his usual standards, to hit the 150+ pages that warrant it being a full-priced book. But the 50-60 pages that actually get into the meat of it are REALLY good, don't get me wrong.
I tried to run the code but failed with "ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (2,) + inhomogeneous part." on "state = np.reshape(state, [1, state_size])", may I know why? Thank you very much!
have you solved this problem? I encountered the same one.
Amazing explanation, thanks!
This is too good!!!
iOKPowerPoint is not a word. It is a name. Being idle too long.
Thanks that was helpful
Hello Jon, I am not finding the code in your Github.. can you please help me. I will be thankful
Simple explanation..you helped me few hours of reading tough paper.thanks
Excellent tutorial. I am struggling with the explanation on the target_f and the mapping. Can someone clarify the intuition of that step? It is clear what it does, but I don't get why is this useful.
Ok, I got it. The network has to be trained to correctly guess the q values.
The best teacher
best java tutorial
I had a mini city app in the side bar. I really loved it being there, but some kind of other download that helped power it went defunct, so now it has gone.
Amazing tutorial. I couldn't imagine of learning complete DQN tutorial in an hour with so precise code.
Hi, first of all, thank you for this great video!!!! Unfortunately i always get the same error message when testing: ValueError: cannot reshape array of size 2 into shape (1,4) I can't get this solved, can anyone help? Thanks in advance!
have you solved this problem? I encountered the same one.
Good stuff!
52:24 - you wrote something extremely confusing in probably the most important part of this tutorial! why would you calculate target_f=self.model.predict(state) and then replace the most important value of it with target in "target_f[0][action]=target?!? I'm really banging my head on the table here
did you find the answer for this issue? i could not understand the same point.
yeh i got it now after doing my thesis haha. This following explanation assumes that everything is deterministic in the environment, so if I took action X to get to next_state Y, I will definitely end up in next_state Y. Explanation: "target" is a prediction of how good your current state-action pair is using the bellman equation (so both current state and action taken are put into account). So, if at your current state you can take 4 different actions (so 4 possible state-action pairs), the value "target" is representing one of them (relevant to the specific action taken, or in other words relevant to the next state you ended up in). "target_f" represents predictions of all possible reward values of the current state (so it holds 4 values if you have 4 possible state-action pairs) based solely on the outputs of the NN. But since you already know that you are going to take "action" at the current state (its a variable in the "for" loop), you have better information now on the specific state-action pair relevant to the action you're taking - so might as well update the value inside "target_f" relevant to the action you took ("action") with your calculation using the bellman equation. What may help you to understand this better is that imagine right in the beginning of the training process, the NN spews out absolute garbage because it has merely been trained or updated. So at least you can change some of the values it predicts by values holding more "accurate" information (the variable "target" for instance includes the term "reward" which is actual measured info, not predicted info). @@caganyigitdeliktas292
Hey sir, very good tutorials. Pls i'm having issues with docker, i make couple of research and found out that i need to enable virtualization on my PC; I try enabling it ,even went as far as contacting the laptop brand support but no assistance was working. Pls, is there any alternative that you can suggest for me.. This whole stuff is becoming frustrating🙏
Really great explanation! Thank you so much @Jon
I just need one clarification regarding this. How much time did it take to reach 1000 episodes ? It seems to be fairly quick. I am trying to solve it but it takes me around two hours. I don't know why. Maybe, the dependencies, the versions are not compatible with each other but I am not sure. Can you please help and clarify this for me ? I am using tensorflow 2.9, ide is pycharm and my processor is Intel i7 11800h. I've tried it using gpu as well but it takes me 1-1.5 hours.
Muhteşem anlatım - Excellent presentation !
Thanks for the lecture. Very educative. I am confused by the gradient ascent. How does the keras fit know it is supposed to do gradient ascent and not gradient descent?
In CartPole-v1 the maximum length of an episode is 500 so the bar has been raised now.
Iam looking on this video 2022
Mister Job aye
seriously this is one of the best videos which i have seen in youtube, thank you so much!
I am looking for the other two videos, anyone can point me to them???
Can you explain how you transform high-level ideas outlined in a product roadmap into definitive items in a product backlog?
Would it be possible to star the software used for that simulation. I am trying to do something similar using keysight Genesys and EM pro with very limited time to learn the ins and outs of those softwares. Thank you.
New Word is shit ... old Word is great.
Hi, Thank you so much for the great video, I can see from your talk is the agile coach at the team level is actually the scrum master, should be the team level coach be the same as the scrum master or a different role called Team Agile Coach
That is exactly what I have been looking for! Thanks a lot!
Nice