Artificial neural networks with Java : tools for building neural network applications / Igor Livshin.

Format:

Book

Author/Creator:

Livshin, Igor, author.

Language:

English

Subjects (All):

Neural networks (Computer science).

Java (Computer program language).

Physical Description:

1 online resource (635 pages)

Edition:

2nd ed.

Place of Publication:

[Place of publication not identified] : Apress, [2022]

Summary:

Develop neural network applications using the Java environment. After learning the rules involved in neural network processing, this second edition shows you how to manually process your first neural network example. The book covers the internals of front and back propagation and helps you understand the main principles of neural network processing. You also will learn how to prepare the data to be used in neural network development and you will be able to suggest various techniques of data preparation for many unconventional tasks. This book discusses the practical aspects of using Java for neural network processing. You will know how to use the Encog Java framework for processing large-scale neural network applications. Also covered is the use of neural networks for approximation of non-continuous functions. In addition to using neural networks for regression, this second edition shows you how to use neural networks for computer vision. It focuses on image recognition such as the classification of handwritten digits, input data preparation and conversion, and building the conversion program. And you will learn about topics related to the classification of handwritten digits such as network architecture, program code, programming logic, and execution. The step-by-step approach taken in the book includes plenty of examples, diagrams, and screenshots to help you grasp the concepts quickly and easily. What You Will Learn Use Java for the development of neural network applications Prepare data for many different tasks Carry out some unusual neural network processing Use a neural network to process non-continuous functions Develop a program that recognizes handwritten digits Who This Book Is For Intermediate machine learning and deep learning developers who are interested in switching to Java.

Contents:

Intro

Table of Contents

About the Author

About the Technical Reviewers

Acknowledgments

Introduction

Part I: Getting Started with Neural Networks

Chapter 1: Learning About Neural Networks

Biological and Artificial Neurons

Activation Functions

Summary

Chapter 2: Internal Mechanics of Neural Network Processing

Function to Be Approximated

Network Architecture

Forward Pass Calculation

Input Record 1

Input Record 2

Input Record 3

Input Record 4

Back-Propagation Pass

Function Derivative and Function Divergent

Most Commonly Used Function Derivatives

Chapter 3: Manual Neural Network Processing

Example: Manual Approximation of a Function at a Single Point

Building the Neural Network

Hidden Layers

Output Layer

Backward Pass Calculation

Calculating Weight Adjustments for the Output-Layer Neurons

Calculating Adjustment for W211

Calculating Adjustment for W212

Calculating Adjustment for W213

Calculating Weight Adjustments for Hidden-Layer Neurons

Calculating Adjustment for W111

Calculating Adjustment for W112

Calculating Adjustment for W121

Calculating Adjustment for W122

Calculating Adjustment for W131

Calculating Adjustment for W132

Updating Network Biases

Back to the Forward Pass

Matrix Form of Network Calculation

Digging Deeper

Mini-Batches and Stochastic Gradient

Part II: Neural Network Java Development Environment

Chapter 4: Configuring Your Development Environment

Installing the Java Environment and NetBeans on Your Windows Machine

Installing the Encog Java Framework

Installing the XChart Package

Chapter 5: Neural Networks Development Using the Java Encog Framework.

Example: Function Approximation Using Java Environment

Normalizing the Input Datasets

Building the Java Program That Normalizes Both Datasets

Building the Neural Network Processing Program

Program Code

Debugging and Executing the Program

Processing Results for the Training Method

Testing the Network

Testing Results

Chapter 6: Neural Network Prediction Outside of the Training Range

Example: Approximating Periodic Functions Outside of the Training Range

Network Architecture for the Example

Program Code for the Example

Example: Correct Way of Approximating Periodic Functions Outside of the Training Range

Preparing the Training Data

Program Code for Example

Training Results for Example

Log of Testing Results for Example 3

Chapter 7: Processing Complex Periodic Functions

Example: Approximation of a Complex Periodic Function

Data Preparation

Reflecting Function Topology in the Data

Training the Network

Chapter 8: Approximating Noncontinuous Functions

Example: Approximating Noncontinuous Functions

Code Fragments for the Training Process

Unsatisfactory Training Results

Approximating the Noncontinuous Function Using the Micro-Batch Method

Program Code for Micro-Batch Processing

Program Code for the getChart() Method

Code Fragment 1 of the Training Method

Code Fragment 2 of the Training Method

Training Results for the Micro-Batch Method

Testing the Processing Logic

Testing the Results for the Micro-Batch Method

Summary.

Chapter 9: Approximation of Continuous Functions with Complex Topology

Example: Approximation of Continuous Functions with Complex Topology Using a Conventional Neural Network Process

Training Processing Results for the Example

Approximation of Continuous Functions with Complex Topology Using the Micro-Batch Method

Program Code for the Example Using the Micro-Batch Method

Example: Approximation of Spiral-like Functions

Approximation of the Same Functions Using Micro-Batch Method

Chapter 10: Using Neural Networks for the Classification of Objects

Example: Classification of Records

Training Dataset

Testing Dataset

Program Code for Data Normalization

Program Code for Classification

Training Results

Chapter 11: The Importance of Selecting the Correct Model

Example: Predicting Next Month's Stock Market Price

Including the Function Topology in the Dataset

Building Micro-Batch Files

Training Process

Testing Logic

Analyzing Testing Results

Chapter 12: Approximation Functions in 3D Space

Example: Approximation Functions in 3D Space

Processing Results

Part III: Introduction to Computer Vision

Chapter 13: Image Recognition

Classification of Handwritten Digits

Preparing the Input Data

Input Data Conversion

Building the Conversion Program

Chapter 14: Classification of Handwritten Digits

Programming Logic

Execution.

Convolution Neural Network

Index.

Notes:

Description based on print version record.

Includes index.

ISBN:

9781523150922

1523150920

9781484273685

1484273680

OCLC:

1281957925