THIS PAGE INCORPORATES CASCADING STYLE SHEET! TO VIEW PAGE CORRECTLY PLEASE UPDATE TO A CSS COMPLIANT BROWSER
 |
Efficient Encoding of Natural Time Varying Images Produces Oriented Space-Time Receptive Fields |
pdf 777 KB
ps.gz 672 KB
ps 3.61 MB
@TechReport{Rao:TR97,
author = {Rajesh P.N. Rao and Dana H. Ballard},
title = {Efficient Encoding of Natural Time Varying Images Produces Oriented Space-Time Receptive Fields},
institution = {comp. Sci. Dept. University of Rochester},
year = {1997},
number = {97.4},
address = {Rochester NY},
month = {August},
abstract = {
The receptive fields of neurons in the mammalian primary visual cortex are oriented not only in
the domain of space, but in most cases, also in the domain of spacetime. While the orientation of a
receptive field in space determines the selectivity of the neuron to image structures at a particular orien
tation, a receptive field's orientation in spacetime characterizes important additional properties such as
velocity and direction selectivity. Previous studies have focused on explaining the spatial receptive field
properties of visual neurons by relating them to the statistical structure of static natural images. In this
report, we examine the possibility that the distinctive spatiotemporal properties of visual cortical neurons
can be understood in terms of a statistically efficient strategy for encoding natural time varying images.
We describe an artificial neural network that attempts to accurately reconstruct its spatiotemporal in
put data while simultaneously reducing the statistical dependencies between its outputs. The network
utilizes spatiotemporally summating neurons and learns efficient sparse distributed representations of
its spatiotemporal input stream by using recurrent lateral inhibition and a simple threshold nonlinearity
for rectification of neural responses. When exposed to natural time varying images, neurons in a simu
lated network developed localized receptive fields oriented in both space and spacetime, similar to the
receptive fields of neurons in the primary visual cortex. }
}