PyTorch: Deep Learning and Artificial Intelligence

Focused View

Lazy Programmer Inc.,Lazy Programmer Team

24:18:06

32 View

1. Introduction

1. Welcome.mp4

04:03

2. Overview and Outline.mp4

13:14

2. Getting Set Up

1.1 Data Links.html

1.2 Github Link.html

1. Get Your Hands Dirty, Practical Coding Experience, Data Links.mp4

08:33

2. How to use Github & Extra Coding Tips (Optional).mp4

11:12

3.1 Code Link.html

3.2 Data Links.html

3.3 Github Link.html

3. Where to get the code, notebooks, and data.mp4

03:23

4. How to Succeed in This Course.mp4

03:04

5. Temporary 403 Errors.mp4

02:57

3. Google Colab

1. Intro to Google Colab, how to use a GPU or TPU for free.mp4

12:33

2. Uploading your own data to Google Colab.mp4

13:12

3. Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn.mp4

11:24

4. Machine Learning and Neurons

1. What is Machine Learning.mp4

14:26

2. Regression Basics.mp4

14:39

3. Regression Code Preparation.mp4

11:45

4. Regression Notebook.mp4

13:14

5. Moores Law.mp4

06:57

6. Moores Law Notebook.mp4

13:51

7. Linear Classification Basics.mp4

15:06

8. Classification Code Preparation.mp4

06:57

9. Classification Notebook.mp4

12:00

10. Saving and Loading a Model.mp4

05:21

11. A Short Neuroscience Primer.mp4

09:51

12. How does a model learn.mp4

10:50

13. Model With Logits.mp4

04:18

14. Train Sets vs. Validation Sets vs. Test Sets.mp4

10:12

15. Suggestion Box.mp4

03:10

5. Feedforward Artificial Neural Networks

1. Artificial Neural Networks Section Introduction.mp4

06:00

2. Forward Propagation.mp4

09:40

3. The Geometrical Picture.mp4

09:43

4. Activation Functions.mp4

17:18

5. Multiclass Classification.mp4

09:40

6. How to Represent Images.mp4

12:21

7. Color Mixing Clarification.mp4

00:54

8. Code Preparation (ANN).mp4

14:57

9. ANN for Image Classification.mp4

18:28

10. ANN for Regression.mp4

10:55

11. How to Choose Hyperparameters.mp4

06:24

6. Convolutional Neural Networks

1. What is Convolution (part 1).mp4

16:38

2. What is Convolution (part 2).mp4

05:56

3. What is Convolution (part 3).mp4

06:41

4. Convolution on Color Images.mp4

15:58

5. CNN Architecture.mp4

20:53

6. CNN Code Preparation (part 1).mp4

17:42

7. CNN Code Preparation (part 2).mp4

08:00

8. CNN Code Preparation (part 3).mp4

05:40

9. CNN for Fashion MNIST.mp4

11:32

10. CNN for CIFAR-10.mp4

08:05

11. Data Augmentation.mp4

09:45

12. Batch Normalization.mp4

05:14

13. Improving CIFAR-10 Results.mp4

10:46

7. Recurrent Neural Networks, Time Series, and Sequence Data

1. Sequence Data.mp4

22:14

2. Forecasting.mp4

10:58

3. Autoregressive Linear Model for Time Series Prediction.mp4

12:15

4. Proof that the Linear Model Works.mp4

04:12

5. Recurrent Neural Networks.mp4

21:31

6. RNN Code Preparation.mp4

13:49

7. RNN for Time Series Prediction.mp4

09:29

8. Paying Attention to Shapes.mp4

09:33

9. GRU and LSTM (pt 1).mp4

17:35

10. GRU and LSTM (pt 2).mp4

11:45

11. A More Challenging Sequence.mp4

10:28

12. RNN for Image Classification (Theory).mp4

04:41

13. RNN for Image Classification (Code).mp4

02:48

14. Stock Return Predictions using LSTMs (pt 1).mp4

12:24

15. Stock Return Predictions using LSTMs (pt 2).mp4

06:16

16. Stock Return Predictions using LSTMs (pt 3).mp4

11:46

17. Other Ways to Forecast.mp4

05:14

8. Natural Language Processing (NLP)

1. Embeddings.mp4

13:12

2. Neural Networks with Embeddings.mp4

03:45

3. Text Preprocessing Concepts.mp4

13:33

4.1 Why bad programmers always need the latest version.html

4. Beginner Blues - PyTorch NLP Version.mp4

10:36

5. (Legacy) Text Preprocessing Code Preparation.mp4

11:53

6. (Legacy) Text Preprocessing Code Example.mp4

07:53

7. Text Classification with LSTMs (V2).mp4

17:42

8. CNNs for Text.mp4

12:07

9. Text Classification with CNNs (V2).mp4

07:16

10. (Legacy) VIP Making Predictions with a Trained NLP Model.mp4

07:37

11. VIP Making Predictions with a Trained NLP Model (V2).mp4

04:21

9. Recommender Systems

1. Recommender Systems with Deep Learning Theory.mp4

10:26

2. Recommender Systems with Deep Learning Code Preparation.mp4

09:38

3. Recommender Systems with Deep Learning Code (pt 1).mp4

08:52

4. Recommender Systems with Deep Learning Code (pt 2).mp4

12:31

5. VIP Making Predictions with a Trained Recommender Model.mp4

04:51

10. Transfer Learning for Computer Vision

1. Transfer Learning Theory.mp4

08:12

2. Some Pre-trained Models (VGG, ResNet, Inception, MobileNet).mp4

04:05

3. Large Datasets.mp4

07:11

4. 2 Approaches to Transfer Learning.mp4

04:52

5. Transfer Learning Code (pt 1).mp4

09:36

6. Transfer Learning Code (pt 2).mp4

07:40

11. GANs (Generative Adversarial Networks)

1. GAN Theory.mp4

16:03

2. GAN Code Preparation.mp4

06:18

3. GAN Code.mp4

09:21

12. Deep Reinforcement Learning (Theory)

1. Deep Reinforcement Learning Section Introduction.mp4

06:34

2. Elements of a Reinforcement Learning Problem.mp4

20:18

3. States, Actions, Rewards, Policies.mp4

09:24

4. Markov Decision Processes (MDPs).mp4

10:07

5. The Return.mp4

04:56

6. Value Functions and the Bellman Equation.mp4

09:53

7. What does it mean to learn.mp4

07:18

8. Solving the Bellman Equation with Reinforcement Learning (pt 1).mp4

09:48

9. Solving the Bellman Equation with Reinforcement Learning (pt 2).mp4

12:04

10. Epsilon-Greedy.mp4

06:09

11. Q-Learning.mp4

14:16

12. Deep Q-Learning DQN (pt 1).mp4

14:05

13. Deep Q-Learning DQN (pt 2).mp4

10:25

14. How to Learn Reinforcement Learning.mp4

05:57

13. Stock Trading Project with Deep Reinforcement Learning

1. Reinforcement Learning Stock Trader Introduction.mp4

05:14

2. Data and Environment.mp4

12:22

3. Replay Buffer.mp4

05:40

4. Program Design and Layout.mp4

06:56

5. Code pt 1.mp4

09:22

6. Code pt 2.mp4

09:40

7. Code pt 3.mp4

06:54

8. Code pt 4.mp4

07:25

9. Reinforcement Learning Stock Trader Discussion.mp4

03:36

14. VIP Uncertainty Estimation

1. Custom Loss and Estimating Prediction Uncertainty.mp4

09:36

2. Estimating Prediction Uncertainty Code.mp4

07:12

15. VIP Facial Recognition

1. Facial Recognition Section Introduction.mp4

03:39

2. Siamese Networks.mp4

10:17

3. Code Outline.mp4

05:05

4. Loading in the data.mp4

05:52

5. Splitting the data into train and test.mp4

04:27

6. Converting the data into pairs.mp4

05:04

7. Generating Generators.mp4

05:06

8. Creating the model and loss.mp4

04:28

9. Accuracy and imbalanced classes.mp4

07:48

10. Facial Recognition Section Summary.mp4

03:32

16. In-Depth Loss Functions

1. Mean Squared Error.mp4

09:11

2. Binary Cross Entropy.mp4

05:58

3. Categorical Cross Entropy.mp4

08:06

17. In-Depth Gradient Descent

1. Gradient Descent.mp4

07:52

2. Stochastic Gradient Descent.mp4

04:36

3. Momentum.mp4

06:10

4. Variable and Adaptive Learning Rates.mp4

11:45

5. Adam (pt 1).mp4

13:15

6. Adam (pt 2).mp4

11:14

18. Extras

1. Where Are The Exercises.mp4

04:03

19. Setting up your Environment (FAQ by Student Request)

1. Pre-Installation Check.mp4

04:12

2. How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow.mp4

17:30

3. Anaconda Environment Setup.mp4

20:20

4. Installing NVIDIA GPU-Accelerated Deep Learning Libraries on your Home Computer.mp4

22:15

20. Extra Help With Python Coding for Beginners (FAQ by Student Request)

1. Beginners Coding Tips.mp4

13:21

2. How to Code Yourself (part 1).mp4

15:54

3. How to Code Yourself (part 2).mp4

09:23

4. Proof that using Jupyter Notebook is the same as not using it.mp4

12:29

21. Effective Learning Strategies for Machine Learning (FAQ by Student Request)

1. How to Succeed in this Course (Long Version).mp4

10:24

2. Is this for Beginners or Experts Academic or Practical Fast or slow-paced.mp4

22:04

3. Machine Learning and AI Prerequisite Roadmap (pt 1).mp4

11:18

4. Machine Learning and AI Prerequisite Roadmap (pt 2).mp4

16:07

22. Appendix FAQ Finale

1. What is the Appendix.mp4

02:48

2. BONUS.mp4

05:31

Description

Neural Networks for Computer Vision, Time Series Forecasting, NLP, GANs, Reinforcement Learning, and More!

What You'll Learn?

Artificial Neural Networks (ANNs) / Deep Neural Networks (DNNs)
Predict Stock Returns
Time Series Forecasting
Computer Vision
How to build a Deep Reinforcement Learning Stock Trading Bot
GANs (Generative Adversarial Networks)
Recommender Systems
Image Recognition
Convolutional Neural Networks (CNNs)
Recurrent Neural Networks (RNNs)
Natural Language Processing (NLP) with Deep Learning
Demonstrate Moore's Law using Code
Transfer Learning to create state-of-the-art image classifiers

Who is this for?

Beginners to advanced students who want to learn about deep learning and AI in PyTorch

What You Need to Know?

Know how to code in Python and Numpy

For the theoretical parts (optional), understand derivatives and probability

More details

Description
Welcome to PyTorch:Â Deep Learning and Artificial Intelligence!

Although Google's Deep Learning library Tensorflow has gained massive popularity over the past few years, PyTorch has been the library of choice for professionals and researchers around the globe for deep learning and artificial intelligence.
Is it possible that Tensorflow is popular only because Google is popular and used effective marketing?
Why did Tensorflow change so significantly between version 1 and version 2?Â Was there something deeply flawed with it, and are there still potential problems?
It is less well-known that PyTorch is backed by another Internet giant, Facebook (specifically, the Facebook AIÂ Research Lab - FAIR). So if you want a popular deep learning library backed by billion dollar companies and lots of community support, you can't go wrong with PyTorch. And maybe it's a bonus that the library won't completely ruin all your old code when it advances to the next version. ;)
On the flip side, it is very well-known that all the top AI shops (ex. OpenAI, Apple, and JPMorgan Chase) use PyTorch. OpenAI just recently switched to PyTorch in 2020, a strong sign that PyTorch is picking up steam.
If you are a professional, you will quickly recognize that building and testing new ideas is extremely easy with PyTorch, while it can be pretty hard in other libraries that try to do everything for you. Oh, and it's faster.

Deep Learning has been responsible for some amazing achievements recently, such as:
Generating beautiful, photo-realistic images of people and things that never existed (GANs)
Beating world champions in the strategy game Go, and complex video games like CS:GO and Dota 2 (Deep Reinforcement Learning)
Self-driving cars (Computer Vision)
Speech recognition (e.g. Siri) and machine translation (Natural Language Processing)
Even creating videos of people doing and saying things they never did (DeepFakes - a potentially nefarious application of deep learning)

This course is for beginner-level students all the way up to expert-level students. How can this be?
If you've just taken my free Numpy prerequisite, then you know everything you need to jump right in. We will start with some very basic machine learning models and advance to state of the art concepts.
Along the way, you will learn about all of the major deep learning architectures, such as Deep Neural Networks, Convolutional Neural Networks (image processing), and Recurrent Neural Networks (sequence data).
Current projects include:
Natural Language Processing (NLP)
Recommender Systems
Transfer Learning for Computer Vision
Generative Adversarial Networks (GANs)
Deep Reinforcement Learning Stock Trading Bot
Even if you've taken all of my previous courses already, you will still learn about how to convert your previous code so that it uses PyTorch, and there are all-new and never-before-seen projects in this course such as time series forecasting and how to do stock predictions.
This course is designed for students who want to learn fast, but there are also "in-depth" sections in case you want to dig a little deeper into the theory (like what is a loss function, and what are the different types of gradient descent approaches).
I'm taking the approach that even if you are not 100% comfortable with the mathematical concepts, you can still do this! In this course, we focus more on the PyTorch library, rather than deriving any mathematical equations. IÂ have tons of courses for that already, so there is no need to repeat that here.

Instructor's Note: This course focuses on breadth rather than depth, with less theory in favor of building more cool stuff. If you are looking for a more theory-dense course, this is not it. Generally, for each of these topics (recommender systems, natural language processing, reinforcement learning, computer vision, GANs, etc.) I already have courses singularly focused on those topics.

Thanks for reading, and Iâ€™ll see you in class!

WHATÂ ORDERÂ SHOULDÂ IÂ TAKEÂ YOURÂ COURSESÂ IN?:
Check out the lecture "Machine Learning and AIÂ Prerequisite Roadmap" (available in the FAQ of any of my courses, including the free Numpy course)

UNIQUEÂ FEATURES
Every line of code explained in detail - email me any time if you disagree
No wasted time "typing" on the keyboard like other courses - let's be honest, nobody can really write code worth learning about in just 20 minutes from scratch
Not afraid of university-level math - get important details about algorithms that other courses leave out
Who this course is for:
Beginners to advanced students who want to learn about deep learning and AI in PyTorch

User Reviews

Rating

average 0

Total votes0

Focused display

Today, I spend most of my time as an artificial intelligence and machine learning engineer with a focus on deep learning, although I have also been known as a data scientist, big data engineer, and full stack software engineer.I received my first masters degree over a decade ago in computer engineering with a specialization in machine learning and pattern recognition. I received my second masters degree in statistics with applications to financial engineering.Experience includes online advertising and digital media as both a data scientist (optimizing click and conversion rates) and big data engineer (building data processing pipelines). Some big data technologies I frequently use are Hadoop, Pig, Hive, MapReduce, and Spark.I've created deep learning models to predict click-through rate and user behavior, as well as for image and signal processing and modeling text.My work in recommendation systems has applied Reinforcement Learning and Collaborative Filtering, and we validated the results using A/B testing.I have taught undergraduate and graduate students in data science, statistics, machine learning, algorithms, calculus, computer graphics, and physics for students attending universities such as Columbia University, NYU, Hunter College, and The New School. Multiple businesses have benefitted from my web programming expertise. I do all the backend (server), frontend (HTML/JS/CSS), and operations/deployment work. Some of the technologies I've used are: Python, Ruby/Rails, PHP, Bootstrap, jQuery (Javascript), Backbone, and Angular. For storage/databases I've used MySQL, Postgres, Redis, MongoDB, and more.

Lazy Programmer Team

Instructor's Courses

Today, I spend most of my time as an artificial intelligence and machine learning engineer with a focus on deep learning, although I have also been known as a data scientist, big data engineer, and full stack software engineer.I received my first masters degree over a decade ago in computer engineering with a specialization in machine learning and pattern recognition. I received my second masters degree in statistics with applications to financial engineering.Experience includes online advertising and digital media as both a data scientist (optimizing click and conversion rates) and big data engineer (building data processing pipelines). Some big data technologies I frequently use are Hadoop, Pig, Hive, MapReduce, and Spark.I've created deep learning models to predict click-through rate and user behavior, as well as for image and signal processing and modeling text.My work in recommendation systems has applied Reinforcement Learning and Collaborative Filtering, and we validated the results using A/B testing.I have taught undergraduate and graduate students in data science, statistics, machine learning, algorithms, calculus, computer graphics, and physics for students attending universities such as Columbia University, NYU, Hunter College, and The New School.Multiple businesses have benefitted from my web programming expertise. I do all the backend (server), frontend (HTML/JS/CSS), and operations/deployment work. Some of the technologies I've used are: Python, Ruby/Rails, PHP, Bootstrap, jQuery (Javascript), Backbone, and Angular. For storage/databases I've used MySQL, Postgres, Redis, MongoDB, and more.

Udemy

View courses Udemy

Students take courses primarily to improve job-related skills.Some courses generate credit toward technical certification. Udemy has made a special effort to attract corporate trainers seeking to create coursework for employees of their company.