Share Email Print

Proceedings Paper

Art 2: Self-Organization Of Stable Category Recognition Codes For Analog Input Patterns
Author(s): Gail A. Carpenter; Stephen Grossberg
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Adaptive resonance architectures are neural networks that self-organize stable pattern recognition codes in real-time in response to arbitrary sequences of input patterns. This article introduces ART 2, a class of adaptive resonance architectures which rapidly self-organize pattern recognition categories in response to arbitrary sequences of either analog of binary input patterns. In order to cope with arbitrary sequences of analog input patterns, ART 2 architectures embody solutions to a number of design principles, such as the stability-plasticity tradeoff, the search-direct access tradeoff, and the match-reset tradeoff. In these architectures, top-down learned expectation and matching mechanisms are critical in self-stabilizing the code learning process. A parallel search scheme updates itself adaptively as the learning process unfolds, and realizes a form of real-time hypothesis discovery, testing, learning, and recognition. After learning self-stabilizes, the search process is automatically disengaged. Thereafter input patterns directly access their recognition codes without any search. Thus recognition time for familiar inputs does not increase with the complexity of the learned code. A novel input pattern can directly access a category if it shares invariant properties with the set of familiar exemplars of that category. A parameter called the attentional vigilance parameter determines how fine the categories will be. If vigilance increases (decreases) due to environmental feedback, then the system automatically searches for and learns finer (coarser) recognition categories. Gain control parameters enable the architecture to suppress noise up to a prescribed level. The architecture's global design enables it to learn effectively despite the high degree of nonlinearity of such mechanisms.

Paper Details

Date Published: 19 February 1988
PDF: 9 pages
Proc. SPIE 0848, Intelligent Robots and Computer Vision VI, (19 February 1988); doi: 10.1117/12.942747
Show Author Affiliations
Gail A. Carpenter, Northeastern University (United States)
Stephen Grossberg, Boston University (United States)

Published in SPIE Proceedings Vol. 0848:
Intelligent Robots and Computer Vision VI
David P. Casasent; Ernest L. Hall, 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?