Learning and disrupting invariance in visual recognition with a temporal association rule

Frontiers in Computational Neuroscience

卷:6

Tomaso ePoggio¹  Joel Z Leibo¹  Leyla eIsik¹ 

[1] Massachusetts Institute of Technology;

关键词: Vision;    object recognition;    invariance;    Trace rule;    Cortical models;    Inferotemporal cortex;   

DOI  :  10.3389/fncom.2012.00037

来源: DOAJ

【 摘 要 】

Learning by temporal association rules such as Foldiak’s trace rule is an attractive hypothesis that explains the development of invariance in visual recognition. Consistent with these rules, several recent experiments have shown that invariance can be broken at both the psychophysical and single cell levels. We show a) that temporal association learning provides appropriate invariance in models of object recognition inspired by the visual cortex, b) that we can replicate the invariance disruption experiments using these models with a temporal association learning rule to develop and maintain invariance, and c) that despite dramatic single cell effects, a population of cells is very robust to these disruptions. We argue that these models account for the stability of perceptual invariance despite the underlying plasticity of the system, the variability of the visual world and expected noise in the biological mechanisms.

【 授权许可】

Unknown