Buch, Englisch, 710 Seiten, Format (B × H): 188 mm x 263 mm, Gewicht: 1660 g
Reihe: Bradford Books
Buch, Englisch, 710 Seiten, Format (B × H): 188 mm x 263 mm, Gewicht: 1660 g
Reihe: Bradford Books
ISBN: 978-0-262-03176-9
Verlag: Penguin Random House LLC
Pattern Recognition by Self-Organizing Neural Networks presents
the most recent advances in an area of research that is becoming vitally important in the fields of
cognitive science, neuroscience, artificial intelligence, and neural networks in general. The 19
articles take up developments in competitive learning and computational maps, adaptive resonance
theory, and specialized architectures and biological connections.
Introductory
survey articles provide a framework for understanding the many models involved in various approaches
to studying neural networks. These are followed in Part 2 by articles that form the foundation for
models of competitive learning and computational mapping, and recent articles by Kohonen, applying
them to problems in speech recognition, and by Hecht-Nielsen, applying them to problems in designing
adaptive lookup tables. Articles in Part 3 focus on adaptive resonance theory (ART) networks,
selforganizing pattern recognition systems whose top-down template feedback signals guarantee their
stable learning in response to arbitrary sequences of input patterns. In Part 4, articles describe
embedding ART modules into larger architectures and provide experimental evidence from
neurophysiology, event-related potentials, and psychology that support the prediction that ART
mechanisms exist in the brain.
Contributors: J.-P. Banquet, G.A. Carpenter, S.
Grossberg, R. Hecht-Nielsen, T. Kohonen, B. Kosko, T.W. Ryan, N.A. Schmajuk, W. Singer, D. Stork, C.
von der Malsburg, C.L. Winter.