Reading resources for Neural Networks and Deep Learning

aai-511-deepLearning.md

Book Reference: _Goodfellow, I., Bengio, Y, & Courville, A. (2016). Deep Learning. MIT Press._

Neural Networks and Deep Learning

Module 1: Deep Learning with TensorFlow and PyTorch Fundamentals

_Goodfellow, I., Bengio, Y, & Courville, A. (2016). Deep Learning. MIT Press.

• Chapter 2 (Linear Algebra) (PDF version ).

• Sections 2.1-2.6 (pages 29-40)

  • Errata in Published Editions

• Read the TensorFlow: Broadcasting Guide

• Read the PyTorch: Broadcasting Semantics

Recommended Readings

Here are some suggested resources for learning about developing and implementing math operations of tensors in TensorFlow and PyTorch:

• Introduction to Tensors
• PyTorch website
• Book: Section 2.3 (Linear Algebra of Dive into Deep Learning)
• Torch.Tensor
• TensorFlow: A System for Large-Scale Machine Learning
• PyTorch: An Imperative Style, High-Performance Deep Learning
• TENSORS
• TensorFlow

Required Media

• Watch the What's a Tensor?
• Watch the first 10 minutes of the Deep Learning Chapter 2 - Linear Algebra

![[Machine Learning Study Resources]]

Module 2: Artificial Neural Networks

_Goodfellow, I., Bengio, Y, & Courville, A. (2016). Deep Learning. MIT Press.

• Chapter 6 (Deep Feedforward Networks): pages 164-223

• Errata in Published Editions

• Read Chapter 2 (How the backpropagation algorithm works) of Neural Networks and Deep Learning course

• Read Python AI: How to Build a Neural Network & Make Predictions

• Read Neural network models (supervised)

Required Media

• Watch the But What is a Neural Network? video. (19:13)
• Interact with the TensorFlow Neural Network Playground

Module 3: Recurrent Neural Networks

_Goodfellow, I., Bengio, Y, & Courville, A. (2016). Deep Learning. MIT Press.

• Chapter 10 (Sequence Modeling: Recurrent and Recursive Nets): pages 367-387 (PDF version )

• Read Understanding LSTM Networks

• Read The Unreasonable Effectiveness of Recurrent Neural Networks

• Examine The Ultimate Guide to Recurrent Neural Networks in Python

• Examine Working with RNNs

Required Media

• Watch The Recurrent Neural Networks

Module 4: Convolutional Neural Networks

_Goodfellow, I., Bengio, Y, & Courville, A. (2016). Deep Learning. MIT Press.

• Chapter 9. (Convolutional Networks): pages 326-341

• Errata in Published Editions

• Read ImageNet Classification with Deep Convolutional Neural Networks

• ReadChapter 4 (Major Architectures of Deep Networks) of Deep Learning.

• Examine Convolutional Neural Network (CNN)

• Examine Convolutional Neural Networks — Image Classification w. Keras

Required Media

• Watch the How Convolutional Neural Networks Work
• Watch the Friendly Introduction to Convolutional Neural Networks and Image Recognition

Module 5: Natural Language Processing

_Goodfellow, I., Bengio, Y, & Courville, A. (2016). Deep Learning. MIT Press.

• Chapter 12 - Section 12.4 (Natural Language Processing): pages 456-473 (PDF version )

• Errata in Published Editions

• Read TextBlob: Simplified Text Processing

• Read Tutorial: Quickstart

• Read Text Feature Extraction

• Read TensorFlow: Text

Required Media

Watch the Word Vector Representations: word2vec Watch the Word Embedding and Word2Vec

Module 6: Autoencoders

_Goodfellow, I., Bengio, Y, & Courville, A. (2016). Deep Learning. MIT Press.

• Read Chapter 14 (Autoencoders): pages 499-512
• Read Errata in Published Editions
• Read Intro to Autoencoders
• Read Understanding AutoEncoders with an example: A step-by-step tutorial

Required Media

• Watch the What are Autoencoders?
• Watch the Sparse Autoencoder Lecture Part 2

Module 7: Logistic Regression

• Read the Logistic Regression — Detailed Overview Saishruthi Swaminathan's article.
• Read the Deep Learning vs. Linear Regression article.
• Read the Building an End-to-End Logistic Regression

Required Media

• Watch the Logistic Regression (05:59)
• Watch the Logistic Regression | Deep Learning and Neural Networks(06:20)
• Watch the What is Linear and Non-Linear in Machine Learning, Deep Learning (07:20)