Book Image

Python Deep Learning - Second Edition

By : Ivan Vasilev, Daniel Slater, Gianmario Spacagna, Peter Roelants, Valentino Zocca

Book Image

Python Deep Learning - Second Edition

By: Ivan Vasilev, Daniel Slater, Gianmario Spacagna, Peter Roelants, Valentino Zocca

Overview of this book

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.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Machine Learning - an Introduction

Machine Learning - an Introduction

Introduction to machine learning

Different machine learning approaches

Neural networks

Neural Networks

Neural Networks

The need for neural networks

An introduction to neural networks

Training neural networks

Deep Learning Fundamentals

Deep Learning Fundamentals

Introduction to deep learning

Fundamental deep learning concepts

Deep learning algorithms

Applications of deep learning

The reasons for deep learning's popularity

Introducing popular open source libraries

Computer Vision with Convolutional Networks

Computer Vision with Convolutional Networks

Intuition and justification for CNN

Convolutional layers

Stride and padding in convolutional layers

The structure of a convolutional network

Improving the performance of CNNs

A CNN example with Keras and CIFAR-10

Advanced Computer Vision

Advanced Computer Vision

Transfer learning

Advanced network architectures

Capsule networks

Advanced computer vision tasks

Artistic style transfer

Generating Images with GANs and VAEs

Generating Images with GANs and VAEs

Intuition and justification of generative models

Variational autoencoders

Generative Adversarial networks

Recurrent Neural Networks and Language Models

Recurrent Neural Networks and Language Models

Recurrent neural networks

Language modeling

Sequence to sequence learning

Speech recognition

Reinforcement Learning Theory

Reinforcement Learning Theory

RL as a Markov decision process

Finding optimal policies with Dynamic Programming

Monte Carlo methods

Temporal difference methods

Value function approximations

Experience replay

Q-learning in action

Deep Reinforcement Learning for Games

Deep Reinforcement Learning for Games

Introduction to genetic algorithms playing games

Deep Q-learning

Policy gradient methods

Model-based methods

Deep Learning in Autonomous Vehicles

Deep Learning in Autonomous Vehicles

Brief history of AV research

AV introduction

Imitiation driving policy

Driving policy with ChauffeurNet

DL in the Cloud

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Finding optimal policies with Dynamic Programming

Dynamic Programming (DP) is a base for many RL algorithms. The main paradigm of DP algorithms is to use the state- and action-value functions as tools to find the optimal policy, given a fully-known model of the environment. In this section, we'll see how to do that.

Policy evaluation

We'll start with policy evaluation, or how to compute the state-value function, , given a specific policy, π. This task is also known as prediction. As a reminder, we'll assume that the state-value function is a table. We'll implement policy evaluation using the state-value Bellman equation we defined in the Bellman equations section. Let's start:

Input the following...