Home > Store

Building Neural Networks

Register your product to gain access to bonus material or receive a coupon.

Building Neural Networks


  • Sorry, this book is no longer in print.
Not for Sale


  • Copyright 1996
  • Dimensions: 6-1/2" x 9-1/4"
  • Pages: 304
  • Edition: 1st
  • Book
  • ISBN-10: 0-201-53921-7
  • ISBN-13: 978-0-201-53921-9

This practical introduction describes the kinds of real-world problems neural network technology can solve. Surveying a range of neural network applications, the book demonstrates the construction and operation of artificial neural systems. Through numerous examples, the author explains the process of building neural-network applications that utilize recent connectionist developments, and conveys an understanding both of the potential, and the limitations of different network models. Examples are described in enough detail for you to assimilate the information and then use the accumulated experience of others to create your own applications. These examples are deliberately restricted to those that can be easily understood, and recreated, by any reader, even the novice practitioner. In some cases the author describes alternative approaches to the same application, to allow you to compare and contrast their advantages and disadvantages.

Organized by application areas, rather than by specific network architectures or learning algorithms, Builiding Neural Networks shows why certain networks are more suitable than others for solving specific kinds of problems. Skapura also reviews principles of neural information processing and furnishes an operations summary of the most popular neural-network processing models. Finally, the book provides information on the practical aspects of application design, and contains six topic-oriented chapters on specific applications of neural-network systems. These applications include networks that perform:

  • Pattern matching, storage, and recall
  • Business and financial systems
  • Data extraction from images
  • Mechanical process control systems
  • New neural networks that combine pattern matching with fuzzy logic

The book includes application-oriented excercises that further help you see how a neural network solves a problem, and that reinforce your understanding of modeling techniques.



Source Code


Simulators for Building Neural Networks are available:

   simulat.exe          48,652 bytes (binary)
   simulators.sit.hqx   46,331 bytes (ascii)
   simulators.tar.Z     38,145 bytes (binary)

These archives contain the complete set of files for the neural network simulators associated with the book. The identical material is archived in three different forms for the convenience of DOS/Windows (the binary, self-extracting .exe file), Mac (the ascii stuff, binhexed .sit.hqx file), and Unix (the binary, tarred, compressed .tar.Z file)

Help With File Types

Files with the extension ".exe" are self-extracting. You need no extra software to unarchive these files on your DOS or Windows machine. Once transferred, use the syntax:

    filename -d

(the "-d" will preserve directory structure where directories have been created), where "filename" is the name of the file, minus the ".exe" extension.

Files with the extension ".sit.hqx" are archived using the Macintosh-native Stuffit program, and then bin-hexed, making them ASCII files (transferring them as binary won't hurt them, but is redundant). The easiest way to "unbinhex" and "unstuff" them in one go is to use the free program, StuffIt Expander from Aladdin Systems.

Files with the extension ".tar.Z" are archived using the Unix "tar" command, and then compressed. To make them available, first be sure that you are in binary mode before transferring the files (type "binary" at the "ftp>" prompt). Once transferred, use the syntax:

     uncompress filename.tar.Z
     tar xvf filename.tar

Sample Content

Table of Contents



Neural-Network Fundamentals.

Single Neuron Computations.

Network Computations.

Network Simulation.

Foundations Summary.

Suggested Readings.



The Backpropagation Network.

The Counterpropagation Network.

Adaptive Resonance Theory.

The Multidirectional Associative Memory.

The Hopfield Memory.

Network-Learning Summary.

Suggested Readings.


Application Design.

Developing a Data Representation.

Pattern Representation Methods.

Exemplar Analysis.

Training and Performance Evaluation.

A Practical Example.

Application-Design Summary.

Suggested Readings.


Associative Memories.

Associative-Memory Definitions.

Character Recognition.

State-Space Search.

Image Interpolation.

Diagnostic Aids.

Associative-Memory Summary.

Suggested Readings.


Business and Financial Applications.

Financial Modeling.

Market Prediction.

Bond Rating.

Predicting Commodity Futures.

Financial-Applications Summary.

Suggested Readings.


Pattern Classification.


Radar-Signature Classifier.

Prostate-Cancer Detection.

Pattern-Classification Summary.

Suggested Readings.


Image Processing.

Image-Processing Networks.

Gender Recognition from Facial Images.

Imagery Feature Discovery.

Aircraft Tracking in Video Imagery.

Image-Processing Summary.

Suggested Readings.


Process Control and Robotics.

Control Theory.

Cart/Pole Balancer.

Bipedal-Locomotion Control.

Robotic Manipulator Control.

Control-Application Summary.

Suggested Readings.


Fuzzy Neural Systems.

Fuzzy Logic.

Implementation of a Fuzzy Network.

Fuzzy Neural Inference.

Fuzzy Control of BPN Learning.

Fuzzy Neural-System Summary.

Suggested Readings.


Answers to Selected Exercises.

Index. 0201539217T04062001


Submit Errata

More Information

Unlimited one-month access with your purchase
Free Safari Membership