Brain-like problem solving techniques used by neuro-computers are suited to several problems that are hard for conventional architectures. This book, an intermediate level exposition of the exciting world of neuro-computers, presents several case studies using as a benchmark real-world sensor data sets to demonstrate how the new learning paradigm can be used by a neuro-computer designer to evolve solutions that have better fault-tolerance and generalization properties. New genetic operators are introduced that consistently outperform the conventional crossover and mutation based genetic algorithms. Essentially self-contained, this book would be a valuable addition for all engineering students and can be the starting point for new research in this area.