Share Email Print

Proceedings Paper

Use of dynamical networks for pattern recognition
Author(s): Subramania I. Sudharsanan; Malur K. Sundareshan
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

An established way to synthesize associative memory networks is to use dynamical neural networks. For large dimensional problems, the dynamical networks usually are computationally burdensome to design and generally introduce spurious memories. A new architecture that consists of an input linear filter, a hidden layer of dynamical network and an output linear filter is proposed in this paper to alleviate some of the difficulties in designing large dimensional dynamical networks. A learning rule and its simplified version are presented for the design of the network parameters.

Paper Details

Date Published: 1 March 1992
PDF: 10 pages
Proc. SPIE 1707, Applications of Artificial Intelligence X: Knowledge-Based Systems, (1 March 1992); doi: 10.1117/12.56904
Show Author Affiliations
Subramania I. Sudharsanan, IBM Corp. (United States)
Malur K. Sundareshan, Univ. of Arizona (United States)

Published in SPIE Proceedings Vol. 1707:
Applications of Artificial Intelligence X: Knowledge-Based Systems
Gautam Biswas, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?