1 Biological and Machine Vision
The Traditional Machine Learning Approach
Deep Learning for Natural Language Processing
Deep Learning Networks Learn Representations Automatically
A Brief History of Deep Learning for NLP
Computational Representations of Language
One-Hot Representations of Words
Localist Versus Distributed Representations
Elements of Natural Human Language
Arithmetic on Fake Human Faces
Style Transfer: Converting Photos into Monet (and Vice Versa)
Make Your Own Sketches Photorealistic
Creating Photorealistic Images from Text
Image Processing Using Deep Learning
Deep Learning, AI, and Other Beasts
Three Categories of Machine Learning Problems
Popular Deep Reinforcement Learning Environments
Artificial Narrow Intelligence
Artificial General Intelligence
II Essential Theory Illustrated
5 The (Code) Cart Ahead of the (Theory) Horse
A Schematic Diagram of the Network
Designing a Neural Network Architecture
Training a Deep Learning Model
6 Artificial Neurons Detecting Hot Dogs
The Hot Dog / Not Hot Dog Detector
The Most Important Equation in This Book
Modern Neurons and Activation Functions
A Hot Dog-Detecting Dense Network
Forward Propagation Through the First Hidden Layer
Forward Propagation Through Subsequent Layers
The Softmax Layer of a Fast Food-Classifying Network
Revisiting Our Shallow Network
Optimization: Learning to Minimize Cost
Batch Size and Stochastic Gradient Descent
Tuning Hidden-Layer Count and Neuron Count
Model Generalization (Avoiding Overfitting)
A Deep Neural Network in Keras
III Interactive Applications of Deep Learning
The Two-Dimensional Structure of Visual Imagery
Convolutional Filter Hyperparameters
Vanishing Gradients: The Bête Noire of Deep CNNs
Applications of Machine Vision
11 Natural Language Processing
Preprocessing Natural Language Data
Converting All Characters to Lowercase
Removing Stop Words and Punctuation
Creating Word Embeddings with word2vec
The Essential Theory Behind word2vec
Calculating the ROC AUC Metric
Natural Language Classification with Familiar Networks
Standardizing the Length of the Reviews
Networks Designed for Sequential Data
Non-sequential Architectures: The Keras Functional API
12 Generative Adversarial Networks
13 Deep Reinforcement Learning
Essential Theory of Reinforcement Learning
Essential Theory of Deep Q-Learning Networks
Building the Agent’s Neural Network Model
Saving and Loading Model Parameters
Interacting with an OpenAI Gym Environment
Hyperparameter Optimization with SLM Lab
Policy Gradients and the REINFORCE Algorithm
14 Moving Forward with Your Own Deep Learning Projects
Ideas for Deep Learning Projects
Converting an Existing Machine Learning Project
Resources for Further Projects
The Modeling Process, Including Hyperparameter Tuning
Automation of Hyperparameter Search
Approaching Artificial General Intelligence
A Formal Neural Network Notation
The Fundamental Units Within PyTorch
18.209.31.38