Neural networks for pattern recognition / Albert Nigrin.

Format:

Book

Author/Creator:

Nigrin, Albert.

Language:

English

Subjects (All):

Neural networks (Computer science).

Pattern recognition systems.

Self-organizing systems.

Physical Description:

xvii, 413 pages : illustrations ; 24 cm

Place of Publication:

Cambridge, Mass. : MIT Press, [1993]

Summary:

Neural Networks for Pattern Recognition takes to a new level the pioneering work in artificial neural networks by Stephen Grossberg and his colleagues. In a simple and accessible way it extends embedding field theory into areas of machine intelligence that have not been clearly dealt with before. Following a tutorial of existing neural networks for pattern classification, Nigrin expands on these networks to present fundamentally new architectures that perform real-time pattern classification of embedded and synonymous patterns and that will aid in tasks such as vision, speech recognition, sensor fusion, and constraint satisfaction. Nigrin presents the new architectures in two stages. First he presents a network called Sonnet 1 that already achieves important properties such as the ability to learn and segment continuously varied input patterns in real time, to process patterns in a context-sensitive fashion, and to learn new patterns without degrading existing categories. He then removes simplifications inherent in Sonnet 1 and introduces radically new architectures. These architectures have the power to classify patterns that may have similar meanings but that have different external appearances (synonyms). They also have been designed to represent patterns in a distributed fashion, both in short-term and long-term memory.

Notes:

"A Bradford book."

Includes bibliographical references and index.

ISBN:

0262140543

OCLC:

27768477