English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 150 lectures (24h 18m) | 7.83 GB
Neural Networks for Computer Vision, Time Series Forecasting, NLP, GANs, Reinforcement Learning, and More!
Welcome to PyTorch: 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? 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 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. 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
Getting Set Up
3 Get Your Hands Dirty, Practical Coding Experience, Data Links
4 How to use Github & Extra Coding Tips (Optional)
5 Where to get the code, notebooks, and data
6 How to Succeed in This Course
7 Temporary 403 Errors
Google Colab
8 Intro to Google Colab, how to use a GPU or TPU for free
9 Uploading your own data to Google Colab
10 Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn
Machine Learning and Neurons
11 What is Machine Learning
12 Regression Basics
13 Regression Code Preparation
14 Regression Notebook
15 Moore’s Law
16 Moore’s Law Notebook
17 Linear Classification Basics
18 Classification Code Preparation
19 Classification Notebook
20 Saving and Loading a Model
21 A Short Neuroscience Primer
22 How does a model learn
23 Model With Logits
24 Train Sets vs. Validation Sets vs. Test Sets
25 Suggestion Box
Feedforward Artificial Neural Networks
26 Artificial Neural Networks Section Introduction
27 Forward Propagation
28 The Geometrical Picture
29 Activation Functions
30 Multiclass Classification
31 How to Represent Images
32 Color Mixing Clarification
33 Code Preparation (ANN)
34 ANN for Image Classification
35 ANN for Regression
36 How to Choose Hyperparameters
Convolutional Neural Networks
37 What is Convolution (part 1)
38 What is Convolution (part 2)
39 What is Convolution (part 3)
40 Convolution on Color Images
41 CNN Architecture
42 CNN Code Preparation (part 1)
43 CNN Code Preparation (part 2)
44 CNN Code Preparation (part 3)
45 CNN for Fashion MNIST
46 CNN for CIFAR-10
47 Data Augmentation
48 Batch Normalization
49 Improving CIFAR-10 Results
Recurrent Neural Networks, Time Series, and Sequence Data
50 Sequence Data
51 Forecasting
52 Autoregressive Linear Model for Time Series Prediction
53 Proof that the Linear Model Works
54 Recurrent Neural Networks
55 RNN Code Preparation
56 RNN for Time Series Prediction
57 Paying Attention to Shapes
58 GRU and LSTM (pt 1)
59 GRU and LSTM (pt 2)
60 A More Challenging Sequence
61 RNN for Image Classification (Theory)
62 RNN for Image Classification (Code)
63 Stock Return Predictions using LSTMs (pt 1)
64 Stock Return Predictions using LSTMs (pt 2)
65 Stock Return Predictions using LSTMs (pt 3)
66 Other Ways to Forecast
Natural Language Processing (NLP)
67 Embeddings
68 Neural Networks with Embeddings
69 Text Preprocessing Concepts
70 Beginner Blues – PyTorch NLP Version
71 (Legacy) Text Preprocessing Code Preparation
72 (Legacy) Text Preprocessing Code Example
73 Text Classification with LSTMs (V2)
74 CNNs for Text
75 Text Classification with CNNs (V2)
76 (Legacy) VIP Making Predictions with a Trained NLP Model
77 VIP Making Predictions with a Trained NLP Model (V2)
Recommender Systems
78 Recommender Systems with Deep Learning Theory
79 Recommender Systems with Deep Learning Code Preparation
80 Recommender Systems with Deep Learning Code (pt 1)
81 Recommender Systems with Deep Learning Code (pt 2)
82 VIP Making Predictions with a Trained Recommender Model
Transfer Learning for Computer Vision
83 Transfer Learning Theory
84 Some Pre-trained Models (VGG, ResNet, Inception, MobileNet)
85 Large Datasets
86 Approaches to Transfer Learning
87 Transfer Learning Code (pt 1)
88 Transfer Learning Code (pt 2)
GANs (Generative Adversarial Networks)
89 GAN Theory
90 GAN Code Preparation
91 GAN Code
Deep Reinforcement Learning (Theory)
92 Deep Reinforcement Learning Section Introduction
93 Elements of a Reinforcement Learning Problem
94 States, Actions, Rewards, Policies
95 Markov Decision Processes (MDPs)
96 The Return
97 Value Functions and the Bellman Equation
98 What does it mean to “learn”
99 Solving the Bellman Equation with Reinforcement Learning (pt 1)
100 Solving the Bellman Equation with Reinforcement Learning (pt 2)
101 Epsilon-Greedy
102 Q-Learning
103 Deep Q-Learning DQN (pt 1)
104 Deep Q-Learning DQN (pt 2)
105 How to Learn Reinforcement Learning
Stock Trading Project with Deep Reinforcement Learning
106 Reinforcement Learning Stock Trader Introduction
107 Data and Environment
108 Replay Buffer
109 Program Design and Layout
110 Code pt 1
111 Code pt 2
112 Code pt 3
113 Code pt 4
114 Reinforcement Learning Stock Trader Discussion
VIP Uncertainty Estimation
115 Custom Loss and Estimating Prediction Uncertainty
116 Estimating Prediction Uncertainty Code
VIP Facial Recognition
117 Facial Recognition Section Introduction
118 Siamese Networks
119 Code Outline
120 Loading in the data
121 Splitting the data into train and test
122 Converting the data into pairs
123 Generating Generators
124 Creating the model and loss
125 Accuracy and imbalanced classes
126 Facial Recognition Section Summary
In-Depth Loss Functions
127 Mean Squared Error
128 Binary Cross Entropy
129 Categorical Cross Entropy
In-Depth Gradient Descent
130 Gradient Descent
131 Stochastic Gradient Descent
132 Momentum
133 Variable and Adaptive Learning Rates
134 Adam (pt 1)
135 Adam (pt 2)
Extras
136 Where Are The Exercises
Setting up your Environment (FAQ by Student Request)
137 Pre-Installation Check
138 How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
139 Anaconda Environment Setup
140 Installing NVIDIA GPU-Accelerated Deep Learning Libraries on your Home Computer
Extra Help With Python Coding for Beginners (FAQ by Student Request)
141 Beginner’s Coding Tips
142 How to Code Yourself (part 1)
143 How to Code Yourself (part 2)
144 Proof that using Jupyter Notebook is the same as not using it
Effective Learning Strategies for Machine Learning (FAQ by Student Request)
145 How to Succeed in this Course (Long Version)
146 Is this for Beginners or Experts Academic or Practical Fast or slow-paced
147 Machine Learning and AI Prerequisite Roadmap (pt 1)
148 Machine Learning and AI Prerequisite Roadmap (pt 2)
Appendix FAQ Finale
149 What is the Appendix
150 BONUS
Resolve the captcha to access the links!