PyTorch: Deep Learning and Artificial Intelligence

PyTorch: Deep Learning and Artificial Intelligence
PyTorch: Deep Learning and Artificial Intelligence
English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 22.5 Hours | 7.27 GB

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

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? 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 AI 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 Tensorflow 2.0, 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. I 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.

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
Table of Contents

Introduction
1 Welcome
2 Overview and Outline
3 Where to get the Code

Google Colab
4 Intro to Google Colab, how to use a GPU or TPU for free
5 Uploading your own data to Google Colab
6 Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn

Machine Learning and Neurons
7 What is Machine Learning
8 Saving and Loading a Model
9 A Short Neuroscience Primer
10 How does a model learn
11 Model With Logits
12 Train Sets vs. Validation Sets vs. Test Sets
13 Regression Basics
14 Regression Code Preparation
15 Regression Notebook
16 Moore’s Law
17 Moore’s Law Notebook
18 Linear Classification Basics
19 Classification Code Preparation
20 Classification Notebook

Feedforward Artificial Neural Networks
21 Artificial Neural Networks Section Introduction
22 Forward Propagation
23 The Geometrical Picture
24 Activation Functions
25 Multiclass Classification
26 How to Represent Images
27 Code Preparation (ANN)
28 ANN for Image Classification
29 ANN for Regression

Convolutional Neural Networks
30 What is Convolution (part 1)
31 CNN for CIFAR-10
32 Data Augmentation
33 Batch Normalization
34 Improving CIFAR-10 Results
35 What is Convolution (part 2)
36 What is Convolution (part 3)
37 Convolution on Color Images
38 CNN Architecture
39 CNN Code Preparation (part 1)
40 CNN Code Preparation (part 2)
41 CNN Code Preparation (part 3)
42 CNN for Fashion MNIST

Recurrent Neural Networks, Time Series, and Sequence Data
43 Sequence Data
44 GRU and LSTM (pt 2)
45 A More Challenging Sequence
46 RNN for Image Classification (Theory)
47 RNN for Image Classification (Code)
48 Stock Return Predictions using LSTMs (pt 1)
49 Stock Return Predictions using LSTMs (pt 2)
50 Stock Return Predictions using LSTMs (pt 3)
51 Other Ways to Forecast
52 Forecasting
53 Autoregressive Linear Model for Time Series Prediction
54 Proof that the Linear Model Works
55 Recurrent Neural Networks
56 RNN Code Preparation
57 RNN for Time Series Prediction
58 Paying Attention to Shapes
59 GRU and LSTM (pt 1)

Natural Language Processing (NLP)
60 Embeddings
61 Neural Networks with Embeddings
62 Text Preprocessing (pt 1)
63 Text Preprocessing (pt 2)
64 Text Preprocessing (pt 3)
65 Text Classification with LSTMs
66 CNNs for Text
67 Text Classification with CNNs
68 VIP Making Predictions with a Trained NLP Model

Recommender Systems
69 Recommender Systems with Deep Learning Theory
70 Recommender Systems with Deep Learning Code Preparation
71 Recommender Systems with Deep Learning Code (pt 1)
72 Recommender Systems with Deep Learning Code (pt 2)
73 VIP Making Predictions with a Trained Recommender Model

Transfer Learning for Computer Vision
74 Transfer Learning Theory
75 Some Pre-trained Models (VGG, ResNet, Inception, MobileNet)
76 Large Datasets
77 Approaches to Transfer Learning
78 Transfer Learning Code (pt 1)
79 Transfer Learning Code (pt 2)

GANs (Generative Adversarial Networks)
80 GAN Theory
81 GAN Code Preparation
82 GAN Code

Deep Reinforcement Learning (Theory)
83 Deep Reinforcement Learning Section Introduction
84 Epsilon-Greedy
85 Q-Learning
86 Deep Q-Learning DQN (pt 1)
87 Deep Q-Learning DQN (pt 2)
88 How to Learn Reinforcement Learning
89 Elements of a Reinforcement Learning Problem
90 States, Actions, Rewards, Policies
91 Markov Decision Processes (MDPs)
92 The Return
93 Value Functions and the Bellman Equation
94 What does it mean to “learn”
95 Solving the Bellman Equation with Reinforcement Learning (pt 1)
96 Solving the Bellman Equation with Reinforcement Learning (pt 2)

Stock Trading Project with Deep Reinforcement Learning
97 Reinforcement Learning Stock Trader Introduction
98 Data and Environment
99 Replay Buffer
100 Program Design and Layout
101 Code pt 1
102 Code pt 2
103 Code pt 3
104 Code pt 4
105 Reinforcement Learning Stock Trader Discussion

VIP Uncertainty Estimation
106 Custom Loss and Estimating Prediction Uncertainty
107 Estimating Prediction Uncertainty Code

VIP Facial Recognition
108 Facial Recognition Section Introduction
109 Facial Recognition Section Summary
110 Siamese Networks
111 Code Outline
112 Loading in the data
113 Splitting the data into train and test
114 Converting the data into pairs
115 Generating Generators
116 Creating the model and loss
117 Accuracy and imbalanced classes

In-Depth Loss Functions
118 Mean Squared Error
119 Binary Cross Entropy
120 Categorical Cross Entropy

In-Depth Gradient Descent
121 Gradient Descent
122 Stochastic Gradient Descent
123 Momentum
124 Variable and Adaptive Learning Rates
125 Adam

Extras
126 Links To Colab Notebooks
127 Links to VIP Notebooks

Setting up your Environment
128 How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
129 Windows-Focused Environment Setup 2018
130 Installing NVIDIA GPU-Accelerated Deep Learning Libraries on your Home Computer

Appendix FAQ
131 What is the Appendix
132 Is this for Beginners or Experts Academic or Practical Fast or slow-paced
133 How to Code Yourself (part 1)
134 How to Code Yourself (part 2)
135 Proof that using Jupyter Notebook is the same as not using it
136 How to Succeed in this Course (Long Version)
137 What order should I take your courses in (part 1)
138 What order should I take your courses in (part 2)
139 BONUS Where to get discount coupons and FREE deep learning material