English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  Optimal, unsupervised learning in invariant object recognition

Wallis, G. (1997). Optimal, unsupervised learning in invariant object recognition. Neural Computation, 9(4), 883-894. doi:10.1162/neco.1997.9.4.883.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Wallis, GM1, Author           
Affiliations:
1Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497797              

Content

show
hide
Free keywords: -
 Abstract: A means for establishing transformation-invariant representations of objects is proposed and analyzed, in which different views are associated on the basis of the temporal order of the presentation of these views, as well as their spatial similarity. Assuming knowledge of the distribution of presentation times, an optimal linear learning rule is derived. Simulations of a competitive network trained on a character recognition task are then used to highlight the success of this learning rule in relation to simple Hebbian learning and to show that the theory can give accurate quantitative predictions for the optimal parameters for such networks.

Details

show
hide
Language(s):
 Dates: 1997-05
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: URI: http://dl.acm.org/citation.cfm?id=252484
DOI: 10.1162/neco.1997.9.4.883
BibTex Citekey: 390
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Neural Computation
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 9 (4) Sequence Number: - Start / End Page: 883 - 894 Identifier: -