PyTorch: Deep Learning and Artificial Intelligence

Description

In this course, you will 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

Syllabus :

1. Google Colab

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

 

2. Machine Learning and Neurons

• What is Machine Learning?
• Regression Basics
• Regression Code Preparation
• Regression Notebook
• Moore's Law
• Moore's Law Notebook
• Exercise: Real Estate Predictions
• Linear Classification Basics
• Classification Code Preparation
• Classification Notebook
• Exercise: Predicting Diabetes Onset
• Saving and Loading a Model
• A Short Neuroscience Primer
• How does a model "learn"?
• Model With Logits
• Train Sets vs. Validation Sets vs. Test Sets
• Suggestion Box

 

3. Feedforward Artificial Neural Networks

• Artificial Neural Networks Section Introduction
• Forward Propagation
• The Geometrical Picture
• Activation Functions
• Multiclass Classification
• How to Represent Images
• Code Preparation (ANN)
• ANN for Image Classification
• ANN for Regression

 

 

4. Convolutional Neural Networks

• What is Convolution?
• Convolution on Color Images
• CNN Architecture
• CNN Code Preparation
• CNN for Fashion MNIST
• CNN for CIFAR-10
• Data Augmentation
• Batch Normalization
• Improving CIFAR-10 Results

 

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

• Sequence Data
• Forecasting
• Autoregressive Linear Model for Time Series Prediction
• Proof that the Linear Model Works
• Recurrent Neural Networks
• RNN Code Preparation
• RNN for Time Series Prediction
• Paying Attention to Shapes
• GRU and LSTM 
• A More Challenging Sequence
• RNN for Image Classification (Theory)
• RNN for Image Classification (Code)
• Stock Return Predictions using LSTMs
• Other Ways to Forecas

 

5. Natural Language Processing (NLP)

• Embeddings
• Neural Networks with Embeddings
• Text Preprocessing Concepts
• Beginner Blues - PyTorch NLP Version
• (Legacy) Text Preprocessing Code Preparation
• (Legacy) Text Preprocessing Code Example
• (Legacy) Text Classification with LSTMs
• CNNs for Text
• (Legacy) Text Classification with CNNs
• (Legacy) VIP: Making Predictions with a Trained NLP Model
• Exercise: Sentiment Analysis

 

6. Recommender Systems

• Recommender Systems with Deep Learning Theory
• Recommender Systems with Deep Learning Code Preparation
• Recommender Systems with Deep Learning Code
• VIP: Making Predictions with a Trained Recommender Mode

 

7. Transfer Learning for Computer Vision

• Transfer Learning Theory
• Some Pre-trained Models (VGG, ResNet, Inception, MobileNet)
• Large Datasets
• 2 Approaches to Transfer Learning
• Transfer Learning Code 

 

8. GANs (Generative Adversarial Networks)

• GAN Theory
• GAN Code Preparation
• GAN Code

 

9. Deep Reinforcement Learning (Theory)

• Deep Reinforcement Learning Section Introduction
• Elements of a Reinforcement Learning Problem
• States, Actions, Rewards, Policies
• Markov Decision Processes (MDPs)
• The Return
• Value Functions and the Bellman Equation
• What does it mean to “learn”?
• Solving the Bellman Equation with Reinforcement Learning
• Epsilon-Greedy
• Q-Learning
• Deep Q-Learning / DQN 
• How to Learn Reinforcement Learning

 

10. Stock Trading Project with Deep Reinforcement Learning

• Reinforcement Learning Stock Trader Introduction
• Data and Environment
• Replay Buffer
• Program Design and Layout
• Code
• Reinforcement Learning Stock Trader Discussio

 

11.  Uncertainty Estimation

• Custom Loss and Estimating Prediction Uncertainty
• Estimating Prediction Uncertainty Code

 

12.  Facial Recognition

• Facial Recognition Section Introduction
• Siamese Networks
• Code Outline
• Loading in the data
• Splitting the data into train and test
• Converting the data into pairs
• Generating Generators
• Creating the model and loss
• Accuracy and imbalanced classes
• Facial Recognition Section Summary

 

13. In-Depth: Loss Functions

• Mean Squared Error
• Binary Cross Entropy
• Categorical Cross Entropy

 

14. In-Depth: Gradient Descent

• Gradient Descent
• Stochastic Gradient Descent
• Momentum
• Variable and Adaptive Learning Rates
• Adam

 

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

• How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
• Anaconda Environment Setup
• Installing NVIDIA GPU-Accelerated Deep Learning Libraries on your Home Computer

 

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

• How to Code Yourself 
• Proof that using Jupyter Notebook is the same as not using it

 

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

• How to Succeed in this Course (Long Version)
• Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
• Machine Learning and AI Prerequisite Roadmap

 

Show more