Simulating neural networks with Mathematica

Abstract

From the Publisher: application, in the context of the interactive Mathematica environment. Readers will learn how to simulate neural network operations using Mathematica, and will learn techniques for employing Mathematica to assess neural network behavior and performance. For students of neural networks in upper-level undergraduate or beginning graduate courses in computer science, engineering, and related areas. Also for researchers and practitioners interested in using Mathematica as a research tool. Features Teaches the reader about what neural networks are, and how to manipulate them within the Mathematica environment. Shows how Mathematica can be used to implement and experiment with neural network architectures. Addresses a major topic related to neural networks in each chapter, or a specific type of neural network architecture. Contains exercises, suggested projects, and supplementary reading lists with each chapter. Includes Mathematica application programs (?packages?) in Appendix. (Also available electronically from MathSource.) 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