Pub. Date:
MIT Press
Fundamentals of Artificial Neural Networks

Fundamentals of Artificial Neural Networks

by Mohamad Hassoun


Current price is , Original price is $45.0. You

Temporarily Out of Stock Online

Please check back later for updated availability.

This item is available online through Marketplace sellers.

Product Details

ISBN-13: 9780262514675
Publisher: MIT Press
Publication date: 01/01/2003
Series: A Bradford Book
Edition description: New Edition
Pages: 511
Product dimensions: 7.40(w) x 9.20(h) x 1.20(d)
Age Range: 18 Years

About the Author

Mohamad Hassoun is Professor in the Department of Electrical and Computer Engineering at Wayne State University.

Table of Contents

1 Threshold Gates
1.1 Threshold Gates
1.2 Computational Capabilities of Polynomial Threshold Gates
1.3 General Position and the Function Counting Theorem
1.4 Minimal PTG Realization of Arbitrary Switching Functions
1.5 Ambiguity and Generalization
1.6 EXtreme Points
1.7 Summary
2 Computational Capabilities of Artificial Neural Networks
2.1 Some Preliminary Results on Neural Network Mapping Capabilities
2.2 Necessary Lower Bounds on the Size of LTG Networks
2.3 ApproXimation Capabilities of Feedforward Neural Network for
Continuous Functions
2.4 Computational Effectiveness of Neural Networks
2.5 Summary
3 Learning Rules
3.1 Supervised Learning in a Single Unit Setting
3.2 Reinforcement Learning
3.3 Unsupervised Learning
3.4 Competitive Learning
3.5 SelfOrganizing Feature Maps: Topology Preserving
Competitive Learning
3.6 Summary
4 Mathematical Theory of Neural Learning
4.1 Learning as a Search Mechanism
4.2 Mathematical Theory of Learning in a SingleUnit Setting
4.3 Characterization of Additional Learning Rules
4.4 PrincipalComponent Analysis (PCA)
4.5 Theory of Reinforcement Learning
4.6 Theory of Simple Competitive Learning
4.7 Theory of Feature Mapping
4.8 Generalization
4.9 CompleXity of Learning
4.10 SUmmary
5 Adaptive Multilayer Neural Networks I
5.1 Learning Rule for Multilayer Feedforward Neural Networks
5.2 Backprop Enhancements and Variations
5.3 Applications
5.4 EXtensions of Backprop for Temporal Learning
5.5 Summary
6 Adaptive Multilayer NeuralNetworks II
6.1 Radial Basis Function (RBF) Networks
6.2 Cerebeller Model Articulation Controller (CMAC)
6.3 UnitAllocating Adaptive Networks
6.4 Clustering Networks
6.5 Summary
7 Associative Neural Memories
7.1 Basic Associative Neural Memory Models
7.2 DAM Capacity and Retrieval Dynamics
7.3 Characteristics of HighPerformance DAMs
7.4 Other DAM Models
7.5 The DAM as a Gradient Net and Its Application to
Combinatorial Optimization
7.6 Summary
8 Global Search Methods for Neural Networks
8.1 Local versus Global Search
8.2 Simulated AnnealingBased Global Search
8.3 Simulated Annealing for Stochastic Neural Networks
8.4 MeanField Annealing and Deterministic Boltzmann Machines
8.5 Genetic Algorithms in Neural Network Optimization
8.6 Genetic AlgorithmAssisted Supervised Learning
8.7 Summary

Customer Reviews

Most Helpful Customer Reviews

See All Customer Reviews