Forward propagating reinforcement learning: biologically plausible learning 
method for multi-layer networks

Watanabe, M; Masuda, T; Kazuyuki, A

doi:10.1016/S0303-2647(03)00127-8

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsStatisticsRevisionsRelease HistoryDetailsSummary

Released

Journal Article

Forward propagating reinforcement learning: biologically plausible learning method for multi-layer networks

MPS-Authors

http://pubman.mpdl.mpg.de/cone/persons/resource/persons84301

Watanabe, M
Department Physiology of Cognitive Processes, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator

There are no locators available

Fulltext (public)

There are no public fulltexts available

Supplementary Material (public)

There is no public supplementary material available

Citation

Watanabe, M., Masuda, T., & Kazuyuki, A. (2003). Forward propagating reinforcement learning: biologically plausible learning method for multi-layer networks. Biosystems, 71(1-2), 213-220. doi:10.1016/S0303-2647(03)00127-8.

Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-DB9F-8

Abstract

We introduce a biologically plausible method of implementing reinforcementlearning to multi-layer neural networks. The key idea is to spatially localize the synaptic modulation induced by reinforcement signals, proceeding downstream from the initial layer to the final layer. Since reinforcement signals are known to be broadcast signals in the actual brain, we need two key assumptions, inhibitory backward connections and bypass to output units, to spatially localize the effect of delayed reinforcement without breaking the basic laws of neurophysiology.