• Details the importance of the neuro-computing approach to artificial intelligence
• Examines the development of a simple simulator; applies simulation results to real-world data
• Demonstrates how the new learning paradigm can be used by a neuro-computer designer to develop solutions with better fault-tolerance and generalization properties
• Summarizes and highlights the advantages of the optimization approach for supervised learning in feedforward neural network models
• Explores the fundamentals of genetic algorithms and presents the various strategies for training feedforward neural networks
• Describes innovative genetic operators (two-parent MRX, three-parent MRX), mutation scheduling, elitist policy, and hybrid learning schemes

The brain-like architecture of artificial neural networks makes them ideal for tackling problems that are too difficult for conventional architectures, specifically problems that involve pattern recognition or other perceptual tasks.

Neuro-Computers: Optimization Based Learning provides an intermediate-level exposition of the exciting world of neuro-computers. It presents the importance of neuro-computing to artificial intelligence, giving historical background and present-day implementation options. The book demonstrates the superiority of the adaptive search strategy over conventional fixed parameter searches performed by backpropagation algorithms. It then explores global optimization strategy and presents genetic algorithms as viable methods to train neuro computers on non-trivial problems.

This self-contained volume is delivered in a format that is suitable for graduate students, as well as researchers who want to begin work in neuro-computing or related artificial intelligence applications.