Accession Number:

ADA458109

Title:

Computational Models of Object Recognition in Cortex: A Review

Descriptive Note:

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Report Date:

2000-08-07

Pagination or Media Count:

12.0

Abstract:

Understanding how biological visual systems perform object recognition is one of the ultimate goals in computational neuroscience. Among the biological models of recognition the main distinctions are between feedforward and feedback and between object-centered and view-centered. From a computational viewpoint the different recognition tasks -- for instance categorization and identification -- are very similar, representing different trade-offs between specificity and invariance. Thus the different tasks do not strictly require different classes of models. The focus of the review is on feedforward, view-based models that are supported by psychophysical and physiological data.

Subject Categories:

  • Cybernetics
  • Bionics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE