For centuries, people have been fascinated by the possibility of building an artificial system that behaves intelligently. From Mary Shelley's Frankenstein monster to the computer intelligence of HAL in 2001, scientists have been cast in the role of creator of such devices. Now there is a new entry into this arena, neural networks, and Naturally Intelligent Systems explores these systems to see how they work and what they can do.
Neural networks are not computers in any traditional sense, and they have little in common with earlier approaches to the problem of fabricating intelligent behavior. Instead, they are information processing systems that are physically modeled after the structure of the brain and that are trained to perform a task rather than programmed like a computer. Neural networks, in fact, provide a tool with problem-solving capabilities—and limitations—strikingly similar to those of animals and people. In particular, they are successful in applications such as speech, vision, robotics, and pattern recognition.
Naturally Intelligent Systems offers a comprehensive introduction to these exciting systems. It provides a technically accurate, yet down-to-earth discussion of neural networks. No particular mathematical background is necessary; it is written for all interested readers. Naturally Intelligent Systents clearly explains the underlying concepts of key neural network designs, how they are trained, and why they work. It compares their behavior to the natural intelligence found in animals—and people. Throughout, Caudill and Butler bring the field into focus by presenting actual applications that illustrate neural networks' utility in the real world.
A Bradford Book
About the Authors
Maureen Caudill is President of Adaptics, a neural network consulting company in San Diego, and author of the popular "Neural Network Primer" articles that appear regularly in AI Expert.
Charles Butler is a Senior Principal Scientist at Physical Sciences in Alexandria, Virginia. He is a specialist in neural network application development.
"This lighthearted book, which offers plenty of mathematical reasoning but not one equation, is a timely witness to the rise of a new and already flourishing discipline.... A superb nontechnical introduction to the tantalizing prospect of machine-based intelligence."
—Philip Morrison, Scientific American