Python deep learning : next generation techniques to revolutionize computer vision, AI, speech and data analysis / Valentino Zocca [and three others].

Format:

Book

Author/Creator:

Zocca, Valentino, author.

Language:

English

Subjects (All):

Python (Computer program language).

Machine learning.

Neural networks (Computer science).

Physical Description:

1 online resource (383 pages) : illustrations

Edition:

1st edition

Place of Publication:

Birmingham, England ; Mumbai, [India] : Packt, 2017.

System Details:

text file

Biography/History:

Zocca Valentino: Valentino Zocca has a PhD degree and graduated with a Laurea in mathematics from the University of Maryland, USA, and University of Rome, respectively, and spent a semester at the University of Warwick. He started working on high-tech projects of an advanced stereo 3D Earth visualization software with head tracking at Autometric, a company later bought by Boeing. There he developed many mathematical algorithms and predictive models, and using Hadoop he automated several satellite-imagery visualization programs. He has worked as an independent consultant at the U. S. Census Bureau, in the USA and in Italy. Currently, Valentino lives in New York and works as an independent consultant to a large financial company. Spacagna Gianmario: Gianmario Spacagna is a senior data scientist at Pirelli, processing sensors and telemetry data for internet of things (IoT) and connected-vehicle applications. He works closely with tire mechanics, engineers, and business units to analyze and formulate hybrid, physics-driven, and data-driven automotive models. His main expertise is in building ML systems and end-to-end solutions for data products. He holds a master's degree in telematics from the Polytechnic of Turin, as well as one in software engineering of distributed systems from KTH, Stockholm. Prior to Pirelli, he worked in retail and business banking (Barclays), cyber security (Cisco), predictive marketing (AgilOne), and did some occasional freelancing. Slater Daniel: Daniel Slater started programming at age 11, developing mods for the id Software game Quake. His obsession led him to become a developer working in the gaming industry on the hit computer game series Championship Manager. He then moved into finance, working on risk- and high-performance messaging systems. He now is a staff engineer working on big data at Skimlinks to understand online user behavior. He spends his spare time training AI to beat computer games. He talks at tech conferences about deep learning and reinforcement learning; and the name of his blog is Daniel Slater's blog. His work in this field has been cited by Google. Roelants Peter: Peter Roelants holds a master's in computer science with a specialization in AI from KU Leuven. He works on applying deep learning to a variety of problems, such as spectral imaging, speech recognition, text understanding, and document information extraction. He currently works at Onfido as a team leader for the data extraction research team, focusing on data extraction from official documents.

Summary:

Take your machine learning skills to the next level by mastering Deep Learning concepts and algorithms using Python. About This Book Explore and create intelligent systems using cutting-edge deep learning techniques Implement deep learning algorithms and work with revolutionary libraries in Python Get real-world examples and easy-to-follow tutorials on Theano, TensorFlow, H2O and more Who This Book Is For This book is for Data Science practitioners as well as aspirants who have a basic foundational understanding of Machine Learning concepts and some programming experience with Python. A mathematical background with a conceptual understanding of calculus and statistics is also desired. What You Will Learn Get a practical deep dive into deep learning algorithms Explore deep learning further with Theano, Caffe, Keras, and TensorFlow Learn about two of the most powerful techniques at the core of many practical deep learning implementations: Auto-Encoders and Restricted Boltzmann Machines Dive into Deep Belief Nets and Deep Neural Networks Discover more deep learning algorithms with Dropout and Convolutional Neural Networks Get to know device strategies so you can use deep learning algorithms and libraries in the real world In Detail With an increasing interest in AI around the world, deep learning has attracted a great deal of public attention. Every day, deep learning algorithms are used broadly across different industries. The book will give you all the practical information available on the subject, including the best practices, using real-world use cases. You will learn to recognize and extract information to increase predictive accuracy and optimize results. Starting with a quick recap of important machine learning concepts, the book will delve straight into deep learning principles using Sci-kit learn. Moving ahead, you will learn to use the latest open source libraries such as Theano, Keras, Google's TensorFlow, and H20. Use this guide to uncover the difficulties of pattern recognition, scaling data with greater accuracy and discussing deep learning algorithms and techniques. Whether you want to dive deeper into Deep Learning, or want to investigate how to get more out of this powerful technology, you’ll find everything inside. Style and approach Python Machine Learning by example follows practical hands on approach. It walks you through the key elements of Python and its powerful machine learning libraries with the help of real world proje...

Contents:

Cover

Copyright

Credits

About the Authors

About the Reviewer

www.PacktPub.com

Customer Feedback

Table of Contents

Preface

Chapter 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

Chapter 2: Neural Networks

Why neural networks?

Fundamentals

Neurons and layers

Different types of activation function

The back-propagation algorithm

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

Chapter 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

Chapter 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

Chapter 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

Chapter 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 pipeline

Speech as input data

Preprocessing

Acoustic model

CTC

Attention-based models

Decoding

End-to-end models

Bibliography

Chapter 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

Chapter 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

Chapter 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

Chapter 10: Building a Production-ready Intrusion Detection System

What is a data product?

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

Index.

Notes:

Includes index.

Description based on online resource; title from PDF title page (ebrary, viewed May 19, 2017).

ISBN:

9781786460660

1786460661

OCLC:

987379512