Systematically explores the relationship between principal component analysis (PCA) and neural networks. Provides a synergistic examination of the mathematical, algorithmic, application and architectural aspects of principal component neural networks. Using a unified formulation, the authors present neural models performing PCA from the Hebbian learning rule and those which use least squares learning rules such as back-propagation. Examines the principles of biological perceptual systems to explain how the brain works. Every chapter contains a selected list of applications examples from diverse areas.
Explicates the relationship between principle component analysis (PCA) and neural networks, studying issues pertaining to both neural network models, such as network structures and algorithms, and theoretical extensions/generalizations of PCA. Includes reference mathematical appendices. Of interest to readers with background in college calculus and probability theory, in disciplines such as mathematics; statistics; neuropsychology; artificial intelligence; and engineering. Annotation c. Book News, Inc., Portland, OR (booknews.com)