Laurenz Wiskott, PhD
Bernstein Center for Computational Neuroscience Berlin
Institute for Theoretical Biology, Humboldt-University Berlin
will speak on
Is slowness a learning principle for complex cells
in V1 and visual invariances in IT?
Abstract:
Different representations of our visual environment vary on different time
scales. Retinal responses vary quickly because they are very sensitive to
saccades or object motion while representations in the inferior temporal
cortex (IT) display a large degree of invariance and therefore vary more
slowly. Turning this argument around leads to slowness as a learning
principle. By learning input-output functions that generate slowly varying
output signals, units become invariant to frequently occurring
transformations, such as translation, rotation, or illumination changes.
We argue that this is an effective mechanism by which IT could learn its
invariant representations. Interestingly the same principle also leads to
a number of complex-cell receptive-field properties even though invariance
does not seem to be such an issue so early in the visual system. Some of
the simulation results presented here are complemented by analytical
results obtained with variational calculus.
The seminar will take place
in 44 Cummington St. Room 203
on Monday - October 22, 2007
at 4:00pm
Hosted by the
Brain and Vision Research Laboratory