Deep Learning Illustrated · A Visual, Interactive Guide to Artificial Intelligence by Aglaé, Bassens -- Read -- Imperial Library of Trantor

Index

Cover About This E-Book Praise for Deep Learning Illustrated Half Title Series Page Title Page Copyright Page Dedication Page Contents Figures Tables Examples Foreword Preface

How to Read This Book

Acknowledgments About the Authors I: Introducing Deep Learning

1. Biological and Machine Vision

Biological Vision Machine Vision TensorFlow Playground Quick, Draw! Summary

2. Human and Machine Language

Deep Learning for Natural Language Processing Computational Representations of Language Elements of Natural Human Language Google Duplex Summary

3. Machine Art

A Boozy All-Nighter 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 Summary

4. Game-Playing Machines

Deep Learning, AI, and Other Beasts Three Categories of Machine Learning Problems Deep Reinforcement Learning Video Games Board Games Manipulation of Objects Popular Deep Reinforcement Learning Environments Three Categories of AI Summary

II: Essential Theory Illustrated

5. The (Code) Cart Ahead of the (Theory) Horse

Prerequisites Installation A Shallow Network in Keras Summary

6. Artificial Neurons Detecting Hot Dogs

Biological Neuroanatomy 101 The Perceptron Modern Neurons and Activation Functions Choosing a Neuron Summary Key Concepts

7. Artificial Neural Networks

The Input Layer Dense Layers A Hot Dog-Detecting Dense Network The Softmax Layer of a Fast Food-Classifying Network Revisiting Our Shallow Network Summary Key Concepts

8. Training Deep Networks

Cost Functions Optimization: Learning to Minimize Cost Backpropagation Tuning Hidden-Layer Count and Neuron Count An Intermediate Net in Keras Summary Key Concepts

9. Improving Deep Networks

Weight Initialization Unstable Gradients Model Generalization (Avoiding Overfitting) Fancy Optimizers A Deep Neural Network in Keras Regression TensorBoard Summary Key Concepts

III: Interactive Applications of Deep Learning

10. Machine Vision

Convolutional Neural Networks Pooling Layers LeNet-5 in Keras AlexNet and VGGNet in Keras Residual Networks Applications of Machine Vision Summary Key Concepts

11. Natural Language Processing

Preprocessing Natural Language Data Creating Word Embeddings with word2vec The Area under the ROC Curve Natural Language Classification with Familiar Networks Networks Designed for Sequential Data Non-sequential Architectures: The Keras Functional API Summary Key Concepts

12. Generative Adversarial Networks

Essential GAN Theory The Quick, Draw! Dataset The Discriminator Network The Generator Network The Adversarial Network GAN Training Summary Key Concepts

13. Deep Reinforcement Learning

Essential Theory of Reinforcement Learning Essential Theory of Deep Q-Learning Networks Defining a DQN Agent Interacting with an OpenAI Gym Environment Hyperparameter Optimization with SLM Lab Agents Beyond DQN Summary Key Concepts

IV: You and AI

14. Moving Forward with Your Own Deep Learning Projects

Ideas for Deep Learning Projects Resources for Further Projects The Modeling Process, Including Hyperparameter Tuning Deep Learning Libraries Software 2.0 Approaching Artificial General Intelligence Summary

V: Appendices

A. Formal Neural Network Notation B. Backpropagation C. PyTorch

PyTorch Features PyTorch in Practice

Index Credits Code Snippets

← Prev
Back
Next →

← Prev
Back
Next →