Available:*
Library | Item Barcode | Call Number | Material Type | Item Category 1 | Status |
---|---|---|---|---|---|
Searching... | 30000002521668 | QA76.87 F73 1994 | Open Access Book | Book | Searching... |
Searching... | 30000002461477 | QA76.87 F73 1994 | Open Access Book | Book | Searching... |
On Order
Summary
Summary
This book introduces neural networks, their operation and their application, in the context of Mathematica, a mathematical programming language. Readers will learn how to simulate neural network operations using Mathematica and will learn techniques for employing Mathematics to assess neural network behaviour and performance. It shows how this popular and widely available software con be used to explore neural network technology, experiment with various architectures, debug new training algorithms and design techniques for analyzing network performance.
Reviews 1
Choice Review
One of a growing series of books that uses the programming language Mathematica to develop an area. (Arnold O. Allen's Introduction to Computer Performance Analysis with Mathematica, CH, May'94, is another applications example, very readable for those with mathematics background.) To fully understand the subject, one should be familiar with the Mathematica user's manual or S. Wolfram's Mathematica: A System for Doing Mathematics (1988). Freeman is well qualified to write the book under review. His specialty is neural networks (he coauthored, with David Skapura, Neural Networks: Algorithms, Applications, and Programming Techniques, 1991). The complete code for the examples can be found in the appendix; a separate section that follows contains references. Graphical illustrations are in black-and-white and are of good quality. As is typical with most works about Mathematica, the examples presented, for the most part, require long or tedious computations but can be solved relatively easily and quickly with Mathematica. Advanced undergraduate through professional. J. C. Biddle; University of Louisville
Table of Contents
Introduction to Neural Networks and Mathematica |
Training by Error Minimization |
Backpropagation and Its Variants |
Probability and Neural Networks |
Optimization and Constraint Satisfaction with Neural Networks |
Feedback and Recurrent Networks |
Adaptive Resonance Theory |
Genetic Algorithms. 020156629XT04062001 |