How do you make a computer capable of making judgments based on sensory inputs? Instead of building a traditional computer, try emulating the brain. If you're comfortable with college level calculus and statistics as well as knowledgeable about neural networks and perceptrons, Neural Smithing can help. But don't expect any hand-holding: Reed and Marks concentrate on practical hints while staying clear of theoretical explanations. Despite a lack of exercises, this book reads like a graduate level textbook. The first chapters provide a bird's eye view of neural networks and supervised learning, but subsequent chapters quickly zero in on topics in supervised learning, in which systems are "adjusted" to accelerate the learning process. Later chapters discuss specific algorithms and methods, and many include "discussion" or "remarks" sections, containing comments and explanations about what approaches may be more successful than others.