Abstract
An important feature of neural network processing lies in a network’s ability to adapt to a given problem. The adaptation is accomplished by modifying its internal structure through some learning procedure. Neural network models may be classified in one of two types: The learning may be supervised by someone or something that indicates to the network what is expected of it, or the network may be governed by a self-organizing process in which it automatically develops an internal state that reflects the properties of its input environment. Self-organizing systems need no a priori knowledge supplied by a supervisor, and are particularly valuable when the task of the system depends only upon some property of the input data itself.
© 1991 Optical Society of America
PDF ArticleMore Like This
Claus Benkert, Verena Hebler, Ju-Seong Jang, Shakil Rehman, Mark Saffman, and Dana Z. Anderson
CFP3 Conference on Lasers and Electro-Optics (CLEO:S&I) 1991
Dana Z. Anderson, Don Montgomery, Mark Saffman, Anno Hermans, Andrea Tuffli, and Gan Zhou
WB1 Nonlinear Optics (NLO) 1992
Mark Saffman, Claus Benkert, and Dana Z. Anderson
WC6 Photorefractive Materials, Effects, and Devices II (PR) 1991