Python Deep Learning

图书信息

作者	Ivan Vasilev
出版社	Packt Publishing
ISBN	9781789349702
出版时间	2019-01-16
字数	48.1万
分类	进口书,外文原版书,电脑,网络

读书简介

Learn advanced state-of-the-art deep learning techniques and their applications using popular Python libraries Key Features *Build a strong foundation in neural networks and deep learning with Python libraries *Explore advanced deep learning techniques and their applications across computer vision and NLP *Learn how a computer can navigate in complex environments with reinforcement learning Book Description With the surge in artificial intelligence in applications catering to both business and consumer needs, deep learning is more important than ever for meeting current and future market demands. With this book, you’ll explore deep learning, and learn how to put machine learning to use in your projects. This second edition of Python Deep Learning will get you up to speed with deep learning, deep neural networks, and how to train them with high-performance algorithms and popular Python frameworks. You’ll uncover different neural network architectures, such as convolutional networks, recurrent neural networks, long short-term memory (LSTM) networks, and capsule networks. You’ll also learn how to solve problems in the fields of computer vision, natural language processing (NLP), and speech recognition. You'll study generative model approaches such as variational autoencoders and Generative Adversarial Networks (GANs) to generate images. As you delve into newly evolved areas of reinforcement learning, you’ll gain an understanding of state-of-the-art algorithms that are the main components behind popular games Go, Atari, and Dota. By the end of the book, you will be well-versed with the theory of deep learning along with its real-world applications. What you will learn *Grasp the mathematical theory behind neural networks and deep learning processes *Investigate and resolve computer vision challenges using convolutional networks and capsule networks *Solve generative tasks using variational autoencoders and Generative Adversarial Networks *Implement complex NLP tasks using recurrent networks (LSTM and GRU) and attention models *Explore reinforcement learning and understand how agents behave in a complex environment *Get up to date with applications of deep learning in autonomous vehicles Who this book is for This book is for data science practitioners, machine learning engineers, and those interested in deep learning who have a basic foundation in machine learning and some Python programming experience. A background in mathematics and conceptual understanding of calculus and statistics will help you gain maximum benefit from this book.

目录

Title Page

Copyright and Credits

Python Deep Learning Second Edition

About Packt

Why subscribe?

PacktPub.com

Contributors

About the authors

About the reviewer

Packt is searching for authors like you

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Download the color images

Conventions used

Get in touch

Reviews

Machine Learning - an Introduction

Introduction to machine learning

Different machine learning approaches

Supervised learning

Linear and logistic regression

Support vector machines

Decision Trees

Naive Bayes

Unsupervised learning

K-means

Reinforcement learning

Q-learning

Components of an ML solution

Neural networks

Introduction to PyTorch

Summary

Neural Networks

The need for neural networks

An introduction to neural networks

An introduction to neurons

An introduction to layers

Multi-layer neural networks

Different types of activation function

Putting it all together with an example

Training neural networks

Linear regression

Logistic regression

Backpropagation

Code example of a neural network for the XOR function

Summary

Deep Learning Fundamentals

Introduction to deep learning

Fundamental deep learning concepts

Feature learning

Deep learning algorithms

Deep networks

A brief history of contemporary deep learning

Training deep networks

Applications of deep learning

The reasons for deep learning's popularity

Introducing popular open source libraries

TensorFlow

Keras

PyTorch

Using Keras to classify handwritten digits

Using Keras to classify images of objects

Summary

Computer Vision with Convolutional Networks

Intuition and justification for CNN

Convolutional layers

A coding example of convolution operation

Stride and padding in convolutional layers

1D, 2D, and 3D convolutions

1x1 convolutions

Backpropagation in convolutional layers

Convolutional layers in deep learning libraries

Pooling layers

The structure of a convolutional network

Classifying handwritten digits with a convolutional network

Improving the performance of CNNs

Data pre-processing

Regularization

Weight decay

Dropout

Data augmentation

Batch normalization

A CNN example with Keras and CIFAR-10

Summary

Advanced Computer Vision

Transfer learning

Transfer learning example with PyTorch

Advanced network architectures

VGG

VGG with Keras, PyTorch, and TensorFlow

Residual networks

Inception networks

Inception v1

Inception v2 and v3

Inception v4 and Inception-ResNet

Xception and MobileNets

DenseNets

Capsule networks

Limitations of convolutional networks

Capsules

Dynamic routing

Structure of the capsule network

Advanced computer vision tasks

Object detection

Approaches to object detection

Object detection with YOLOv3

A code example of YOLOv3 with OpenCV

Semantic segmentation

Artistic style transfer

Summary

Generating Images with GANs and VAEs

Intuition and justification of generative models

Variational autoencoders

Generating new MNIST digits with VAE

Generative Adversarial networks

Training GANs

Training the discriminator

Training the generator

Putting it all together

Types of GANs

DCGAN

The generator in DCGAN

Conditional GANs

Generating new MNIST images with GANs and Keras

Summary

Recurrent Neural Networks and Language Models

Recurrent neural networks

RNN implementation and training

Backpropagation through time

Vanishing and exploding gradients

Long short-term memory

Gated recurrent units

Language modeling

Word-based models

N-grams

Neural language models

Neural probabilistic language model

word2vec

Visualizing word embedding vectors

Character-based models for generating new text

Preprocessing and reading data

LSTM network

Training

Sampling

Example training

Sequence to sequence learning

Sequence to sequence with attention

Speech recognition

Speech recognition pipeline

Speech as input data

Preprocessing

Acoustic model

Recurrent neural networks

CTC

Decoding

End-to-end models

Summary

Reinforcement Learning Theory

RL paradigms

Differences between RL and other ML approaches

Types of RL algorithms

Types of RL agents

RL as a Markov decision process

Bellman equations

Optimal policies and value functions

Finding optimal policies with Dynamic Programming

Policy evaluation

Policy evaluation example

Policy improvements

Policy and value iterations

Monte Carlo methods

Policy evaluation

Exploring starts policy improvement

Epsilon-greedy policy improvement

Temporal difference methods

Policy evaluation

Control with Sarsa

Control with Q-learning

Double Q-learning

Value function approximations

Value approximation for Sarsa and Q-learning

Improving the performance of Q-learning

Fixed target Q-network

Experience replay

Q-learning in action

Summary

Deep Reinforcement Learning for Games

Introduction to genetic algorithms playing games

Deep Q-learning

Playing Atari Breakout with Deep Q-learning

Policy gradient methods

Monte Carlo policy gradients with REINFORCE

Policy gradients with actor–critic

Actor-Critic with advantage

Playing cart pole with A2C

Model-based methods

Monte Carlo Tree Search

Playing board games with AlphaZero

Summary

Deep Learning in Autonomous Vehicles

Brief history of AV research

AV introduction

Components of an AV system

Sensors

Deep learning and sensors

Vehicle localization

Planning

Imitiation driving policy

Behavioral cloning with PyTorch

Driving policy with ChauffeurNet

Model inputs and outputs

Model architecture

Training

DL in the Cloud

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think