This key "user-friendly" feature notwithstanding, the book provides a full level of explanation of the technical aspects of the subject, which non-mathematical rivals usually fail to provide, thereby leaving those areas obscure. Although the study of neural networks is underpinned by ideas that are often best described mathematically, the fundamentals of the subject are accessible without the full mathematical apparatus, as this treatment amply demonstrates. The book provides comprehensive coverage of the following key areas: artificial neurons as models of their real counterparts; the geometry of network action in pattern space; gradient descent methods, including back-propagation; associative memory and Hopfield nets; and self-organization and feature maps. The traditionally difficult topic of adaptive resonance theory is clarified within a hierarchical description of its operation, which disentangles features specific to separate levels of discussion. Finally, a chapter is devoted to organizing the study of neural networks in various ways, and it attempts to overcome the general impression that it is a loose-knit collection of structures and recipes. The primary aim of the book