Optimal, unsupervised learning in invariant object recognition

Wallis, GM; Baddeley, R

doi:10.1162/neco.1997.9.4.883

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Journal Article

Optimal, unsupervised learning in invariant object recognition

MPS-Authors

/persons/resource/persons84297

Wallis, GM
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

https://www.mitpressjournals.org/doi/pdf/10.1162/neco.1997.9.4.883
(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

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

Cite as: https://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.