Conference proceeding
Dynamically stable associative learning: a neurobiologically based ANN and its applications
Proceedings of SPIE, Vol.1710(1), pp.165-176
Science of Artificial Neural Networks
07/01/1992
DOI: 10.1117/12.140082
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 b
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.
Details
- Title: Subtitle
- Dynamically stable associative learning: a neurobiologically based ANN and its applications
- Creators
- Thomas P Vogl - Environmental Research Institute of MichiganKim L Blackwell - Environmental Research Institute of MichiganGarth Barbour - Environmental Research Institute of MichiganDaniel L Alkon - National Institutes of Health
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of SPIE, Vol.1710(1), pp.165-176
- Conference
- Science of Artificial Neural Networks
- DOI
- 10.1117/12.140082
- ISSN
- 0277-786X
- eISSN
- 1996-756X
- Language
- English
- Date published
- 07/01/1992
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Iowa Neuroscience Institute
- Record Identifier
- 9984446065902771
Metrics
52 Record Views