Artificial Neural Networks with Java: Tools for Building Neural Network Applications

✍ Scribed by Igor Livshin

• Publisher: Apress
• Year: 2021
• Tongue: English
• Leaves: 635
• Edition: 2
• Category: Library

✦ Synopsis

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

✦ Table of Contents

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
Summary
Chapter 3: Manual Neural Network Processing
Example: Manual Approximation of a Function at a Single Point
Building the Neural Network
Forward Pass Calculation
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
Hidden Layers
Output Layer
Matrix Form of Network Calculation
Digging Deeper
Mini-Batches and Stochastic Gradient
Summary
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
Summary
Chapter 5: Neural Networks Development Using the Java Encog Framework
Example: Function Approximation Using Java Environment
Network Architecture
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
Digging Deeper
Summary
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
Testing the Network
Example: Correct Way of Approximating Periodic Functions Outside of the Training Range
Preparing the Training Data
Network Architecture for the Example
Program Code for Example
Training Results for Example
Log of Testing Results for Example 3
Summary
Chapter 7: Processing Complex Periodic Functions
Example: Approximation of a Complex Periodic Function
Data Preparation
Reflecting Function Topology in the Data
Network Architecture
Program Code
Training the Network
Testing the Network
Digging Deeper
Summary
Chapter 8: Approximating Noncontinuous Functions
Example: Approximating Noncontinuous Functions
Network Architecture
Program Code
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
Digging Deeper
Summary
Chapter 9: Approximation of Continuous Functions with Complex Topology
Example: Approximation of Continuous Functions with Complex Topology Using a Conventional Neural Network Process
Network Architecture for the Example
Program Code for the Example
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
Network Architecture for the Example
Program Code for Example
Approximation of the Same Functions Using Micro-Batch Method
Summary
Chapter 10: Using Neural Networks for the Classification of Objects
Example: Classification of Records
Training Dataset
Network Architecture
Testing Dataset
Program Code for Data Normalization
Program Code for Classification
Training Results
Testing Results
Summary
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
Network Architecture
Program Code
Training Process
Training Results
Testing Dataset
Testing Logic
Testing Results
Analyzing Testing Results
Summary
Chapter 12: Approximation Functions in 3D Space
Example: Approximation Functions in 3D Space
Data Preparation
Network Architecture
Program Code
Processing Results
Summary
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
Summary
Chapter 14: Classification of Handwritten Digits
Network Architecture
Program Code
Programming Logic
Execution
Convolution Neural Network
Summary
Index