The Variance of Covariance Rules for Associative Matrix Memories and 
Reinforcement Learning

Dayan, P; Sejnowski, TJ

doi:10.1162/neco.1993.5.2.205

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Journal Article

The Variance of Covariance Rules for Associative Matrix Memories and Reinforcement Learning

MPS-Authors

There are no MPG-Authors in the publication available

External Resource

https://www.mitpressjournals.org/doi/pdf/10.1162/neco.1993.5.2.205
(Publisher version)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Dayan, P., & Sejnowski, T. (1993). The Variance of Covariance Rules for Associative Matrix Memories and Reinforcement Learning. Neural computation, 5(2), 205-209. doi:10.1162/neco.1993.5.2.205.

Cite as: https://hdl.handle.net/21.11116/0000-0002-D6FF-E

Abstract

Hebbian synapses lie at the heart of most associative matrix memories (Kohonen 1987; Hinton and Anderson 1981) and are also biologically plausible (Brown et al. 1990; Baudry and Davis 1991). Their analytical and computational tractability make these memories the best understood form of distributed information storage. A variety of Hebbian algorithms for estimating the covariance between input and output patterns has been proposed. This note points out that one class of these involves stochastic estimation of the covariance, shows that the signal-to-noise ratios of the rules are governed by the variances of their estimates, and considers some parallels in reinforcement learning.