de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

Optimal, unsupervised learning in invariant object recognition

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons84297

Wallis,  GM
Department Human Perception, Cognition and Action, 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

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


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-EA20-9
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.