Python Deep Learning电子书

Python Deep Learning

Table of Contents

Python Deep Learning

Credits

About the Authors

About the Reviewer

www.PacktPub.com

eBooks, discount offers, and more

Why subscribe?

Customer Feedback

Preface

What this book covers

What you need for this book

Who this book is for

Conventions

Reader feedback

Customer support

Downloading the example code

Downloading the color images of this book

Errata

Piracy

Questions

1. Machine Learning – An Introduction

What is machine learning?

Different machine learning approaches

Supervised learning

Unsupervised learning

Reinforcement learning

Steps Involved in machine learning systems

Brief description of popular techniques/algorithms

Linear regression

Decision trees

K-means

Naïve Bayes

Support vector machines

The cross-entropy method

Neural networks

Deep learning

Applications in real life

A popular open source package

Summary

2. Neural Networks

Why neural networks?

Fundamentals

Neurons and layers

Different types of activation function

The back-propagation algorithm

Linear regression

Logistic regression

Back-propagation

Applications in industry

Signal processing

Medical

Autonomous car driving

Business

Pattern recognition

Speech production

Code example of a neural network for the function xor

Summary

3. Deep Learning Fundamentals

What is deep learning?

Fundamental concepts

Feature learning

Deep learning algorithms

Deep learning applications

Speech recognition

Object recognition and classification

GPU versus CPU

Popular open source libraries – an introduction

Theano

TensorFlow

Keras

Sample deep neural net code using Keras

Summary

4. Unsupervised Feature Learning

Autoencoders

Network design

Regularization techniques for autoencoders

Denoising autoencoders

Contractive autoencoders

Sparse autoencoders

Summary of autoencoders

Restricted Boltzmann machines

Hopfield networks and Boltzmann machines

Boltzmann machine

Restricted Boltzmann machine

Implementation in TensorFlow

Deep belief networks

Summary

5. Image Recognition

Similarities between artificial and biological models

Intuition and justification

Convolutional layers

Stride and padding in convolutional layers

Pooling layers

Dropout

Convolutional layers in deep learning

Convolutional layers in Theano

A convolutional layer example with Keras to recognize digits

A convolutional layer example with Keras for cifar10

Pre-training

Summary

6. Recurrent Neural Networks and Language Models

Recurrent neural networks

RNN — how to implement and train

Backpropagation through time

Vanishing and exploding gradients

Long short term memory

Language modeling

Word-based models

N-grams

Neural language models

Character-based model

Preprocessing and reading data

LSTM network

Training

Sampling

Example training

Speech recognition

Speech recognition pipeline

Speech as input data

Preprocessing

Acoustic model

Deep belief networks

Recurrent neural networks

CTC

Attention-based models

Decoding

End-to-end models

Summary

Bibliography

7. Deep Learning for Board Games

Early game playing AI

Using the min-max algorithm to value game states

Implementing a Python Tic-Tac-Toe game

Learning a value function

Training AI to master Go

Upper confidence bounds applied to trees

Deep learning in Monte Carlo Tree Search

Quick recap on reinforcement learning

Policy gradients for learning policy functions

Policy gradients in AlphaGo

Summary

8. Deep Learning for Computer Games

A supervised learning approach to games

Applying genetic algorithms to playing games

Q-Learning

Q-function

Q-learning in action

Dynamic games

Experience replay

Epsilon greedy

Atari Breakout

Atari Breakout random benchmark

Preprocessing the screen

Creating a deep convolutional network

Convergence issues in Q-learning

Policy gradients versus Q-learning

Actor-critic methods

Baseline for variance reduction

Generalized advantage estimator

Asynchronous methods

Model-based approaches

Summary

9. Anomaly Detection

What is anomaly and outlier detection?

Real-world applications of anomaly detection

Popular shallow machine learning techniques

Data modeling

Detection modeling

Anomaly detection using deep auto-encoders

H2O

Getting started with H2O

Examples

MNIST digit anomaly recognition

Electrocardiogram pulse detection

Summary

10. Building a Production-Ready Intrusion Detection System

What is a data product?

Training

Weights initialization

Parallel SGD using HOGWILD!

Adaptive learning

Rate annealing

Momentum

Nesterov's acceleration

Newton's method

Adagrad

Adadelta

Distributed learning via Map/Reduce

Sparkling Water

Testing

Model validation

Labeled Data

Unlabeled Data

Summary of validation

Hyper-parameters tuning

End-to-end evaluation

A/B Testing

A summary of testing

Deployment

POJO model export

Anomaly score APIs

A summary of deployment

Summary

Index