The following technical report on learning space-time receptive fields
from natural images is available on the WWW page:
http://www.cs.rochester.edu/u/rao/ or via anonymous ftp (see
instructions below).
Comments and suggestions welcome (This message has been cross-posted -
my apologies to those who received it more than once).
-- Rajesh Rao Internet: rao@cs.rochester.edu Dept. of Computer Science VOX: (716) 275-5492 University of Rochester FAX: (716) 461-2018 Rochester NY 14627-0226 WWW: http://www.cs.rochester.edu/u/rao/===========================================================================
Efficient Encoding of Natural Time Varying Images Produces Oriented Space-Time Receptive Fields
Rajesh P.N. Rao and Dana H. Ballard
Technical Report 97.4 National Resource Laboratory for the Study of Brain and Behavior Department of Computer Science, University of Rochester August 1997
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 space-time. While the orientation of a receptive field in space determines the selectivity of the neuron to image structures at a particular orientation, a receptive field's orientation in space-time 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 input 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 simulated network developed localized receptive fields oriented in both space and space-time, similar to the receptive fields of neurons in the primary visual cortex.
Retrieval information:
FTP-host: ftp.cs.rochester.edu FTP-pathname: /pub/u/rao/papers/space-time.ps.Z WWW URL: http://www.cs.rochester.edu/u/rao/
26 pages; 1040K compressed.
==========================================================================
Anonymous ftp instructions:
>ftp ftp.cs.rochester.edu Connected to anon.cs.rochester.edu. 220 anon.cs.rochester.edu FTP server (Version wu-2.4(3)) ready.
Name: [type 'anonymous' here] 331 Guest login ok, send your complete e-mail address as password.
Password: [type your e-mail address here]
ftp> cd /pub/u/rao/papers/ ftp> get space-time.ps ftp> bye