HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Li, M. Articles by Clark, J. J. Search for Related Content PubMed PubMed Citation Articles by Li, M. Articles by Clark, J. J.

A Temporal Stability Approach to Position and Attention-Shift-Invariant Recognition

limh{at}cim.mcgill.ca, Centre for Intelligent Machines, McGill University, Montréal, Québec, Canada H3A 2A7

James J. Clark

clark{at}cim.mcgill.ca, Centre for Intelligent Machines, McGill University, Montréal, Québec, Canada H3A 2A7

Incorporation of visual-related self-action signals can help neural networks learn invariance. We describe a method that can produce a network with invariance to changes in visual input caused by eye movements and covert attention shifts. Training of the network is controlled by signals associated with eye movements and covert attention shifting. A temporal perceptual stability constraint is used to drive the output of the network toward remaining constant across temporal sequences of saccadic motions and covert attention shifts. We use a four-layer neural network model to perform the position-invariant extraction of local features and temporal integration of invariant presentations of local features in a bottom-up structure. We present results on both simulated data and real images to demonstrate that our network can acquire both position and attention shift invariance.