Share Email Print
cover

Proceedings Paper

Dynamically stable associative learning: a neurobiologically based ANN and its applications
Author(s): Thomas P. Vogl; Kim L. Blackwell; Garth Barbour; Daniel L. Alkon
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Most currently popular artificial neural networks (ANN) are based on conceptions of neuronal properties that date back to the 1940s and 50s, i.e., to the ideas of McCullough, Pitts, and Hebb. Dystal is an ANN based on current knowledge of neurobiology at the cellular and subcellular level. Networks based on these neurobiological insights exhibit the following advantageous properties: (1) A theoretical storage capacity of bN non-orthogonal memories, where N is the number of output neurons sharing common inputs and b is the number of distinguishable (gray shade) levels. (2) The ability to learn, store, and recall associations among noisy, arbitrary patterns. (3) A local synaptic learning rule (learning depends neither on the output of the post-synaptic neuron nor on a global error term), some of whose consequences are: (4) Feed-forward, lateral, and feed-back connections (as well as time-sensitive connections) are possible without alteration of the learning algorithm; (5) Storage allocation (patch creation) proceeds dynamically as associations are learned (self- organizing); (6) The number of training set presentations required for learning is small (< 10) and does not change with pattern size or content; and (7) The network exhibits monotonic convergence, reaching equilibrium (fully trained) values without oscillating. The performance of Dystal on pattern completion tasks such as faces with different expressions and/or corrupted by noise, and on reading hand-written digits (98% accuracy) and hand-printed Japanese Kanji (90% accuracy) is demonstrated.

Paper Details

Date Published: 1 July 1992
PDF: 12 pages
Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140082
Show Author Affiliations
Thomas P. Vogl, Environmental Research Institute of Michigan (United States)
Kim L. Blackwell, Environmental Research Institute of Michigan (United States)
Garth Barbour, Environmental Research Institute of Michigan (United States)
Daniel L. Alkon, National Institutes of Health (United States)


Published in SPIE Proceedings Vol. 1710:
Science of Artificial Neural Networks
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top