English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

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

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.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0002-D6FF-E Version Permalink: http://hdl.handle.net/21.11116/0000-0002-D700-B
Genre: Journal Article

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Dayan, P1, Author              
Sejnowski, TJ, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 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.

Details

show
hide
Language(s):
 Dates: 1993-03
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1162/neco.1993.5.2.205
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Neural computation
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Cambridge, Mass. : MIT Press
Pages: - Volume / Issue: 5 (2) Sequence Number: - Start / End Page: 205 - 209 Identifier: ISSN: 0899-7667
CoNE: https://pure.mpg.de/cone/journals/resource/954925561591