A Biologically Supported Error-Correcting Learning Rule
Abstract
We show that a form of synaptic plasticity recently discovered in slices of the rat visual cortex (Artola et al. 1990) can support an error-correcting learning rule. The rule increases weights when both pre- and postsynaptic units are highly active, and decreases them when pre-synaptic activity is high and postsynaptic activation is less than the threshold for weight increment but greater than a lower threshold. We show that this rule corrects false positive outputs in feedforward associative memory, that in an appropriate opponent-unit architecture it corrects misses, and that it performs better than the optimal Hebbian learning rule reported by Willshaw and Dayan (1990).
Cite
Text
Hancock et al. "A Biologically Supported Error-Correcting Learning Rule." Neural Computation, 1991. doi:10.1162/NECO.1991.3.2.201Markdown
[Hancock et al. "A Biologically Supported Error-Correcting Learning Rule." Neural Computation, 1991.](https://mlanthology.org/neco/1991/hancock1991neco-biologically/) doi:10.1162/NECO.1991.3.2.201BibTeX
@article{hancock1991neco-biologically,
title = {{A Biologically Supported Error-Correcting Learning Rule}},
author = {Hancock, Peter J. B. and Smith, Leslie S. and Phillips, William A.},
journal = {Neural Computation},
year = {1991},
pages = {201-212},
doi = {10.1162/NECO.1991.3.2.201},
volume = {3},
url = {https://mlanthology.org/neco/1991/hancock1991neco-biologically/}
}