Learning and disrupting invariance in visual recognition
Name
MIT-CSAIL-TR-2011-040.pdf
Size
760.55 KB
Format
Adobe PDF
Checksum (MD5)
4d5f2a26581dd7de0fc9539142f4bc6d
Author(s)
Isik, Leyla
Leibo, Joel Z
Poggio, Tomaso
Advisor(s)
Tomaso Poggio
Date Issued
September 10, 2011
Series/Report no.
MIT-CSAIL-TR-2011-040
CBCL-302
Abstract
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 by appropriately altering the visual environment but found puzzling differences in the effects at the psychophysical versus single cell level. We show a) that associative learning provides appropriate invariance in models of object recognition inspired by Hubel and Wiesel 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 we can thereby explain the apparent discrepancies between psychophysics and singe cells effects. 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.
Subjects
vision, object recognition
Terms of Use
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported
Persistent DSpace Link
