| |
Abstract:
(Invited Talks)
Many facets of higher intelligence are realized within the
neocortex of the brain. The organization of neocortex into layers
is one of its most salient anatomical features. These layers
include circuits that form functional columns in cortical maps. A
major unsolved problem concerns the functional utility of such a
Laminar Computing architecture. In particular, how are bottom-up,
top-down, and horizontal interactions organized within cortical
layers to generate adaptive behaviors? This talk describes a neural
model of how these interactions help visual cortex to realize: (1)
the binding process whereby cortex groups distributed data into
coherent object representations; (2) the attentional process
whereby cortex selectively processes important events; and (3) the
developmental and learning processes whereby cortex shapes its
circuits to match environmental constraints. It is proposed that
the mechanisms governing (3) in the infant lead to properties (1)
and (2) in the adult. New computational ideas about feedback
systems suggest how neocortex develops and learns in a stable way,
how the cortex maintains its sensitivity to analog properties of
the environment while it coherently binds distributed information
into emergent structures, and why top-down attention requires
converging bottom-up inputs to fully activate cortical cells,
whereas perceptual groupings do not. Applications of these concepts
to the development of algorithms for the processing of Synthetic
Aperture Radar images and for on-line learning, recognition, and
classification of textured scenes will also be described.
References:
-- Grossberg, S. (1998). How does the cerebral cortex work?
Learning, attention, and grouping by the laminar circuits of visual
cortex. in
Spatial Vision,
in press.
-- Grossberg, S. and Williamson, J.R. (1997). A self-organizing
neural system for learning to recognize textured scenes. In
Vision Research,
in press.
-- Grossberg, S. and Williamson, J.R. (1998). A neural model of
how visual cortex develops a laminar architecture capable of adult
perceptual grouping. Under review. In
Technical Report CAS/CNS TR-98-022.
-- Mingolla, E., Ross, W., and Grossberg, S. (1998). A neural
network for enhancing boundaries and surfaces in synthetic aperture
radar images. In
Neural Networks,
in press.
Supported in part by DARPA, NSF, and ONR.
Stephen Grossberg is Wang Professor of Cognitive and Neural
Systems and Professor of Mathematics, Psychology, and Biomedical
Engineering at Boston University. He is the founder and Director
of the Center for Adaptive Systems, founder and Chairman the
Department of Cognitive and Neural Systems, founder and first
President of the International Neural Network Society, and
founder and co-Editor-in-Chief of the journal Neural Networks.
Grossberg is also an editor of many other journals, including
Journal of Cognitive Neuroscience, Behavioral and Brain Sciences,
Cognitive Brain Research, Neural Computation, and IEEE
Transactions on Neural Networks. He was general chairman of the
IEEE First International Conference on Neural Networks. He
received the 1991 IEEE Neural Network Pioneer award, the 1992
INNS Leadership Award, and the 1992 Thinking Technology Award of
the Boston Computer Society. He was elected a Fellow of the
American Psychological Association in 1994 and a member of the
Society of Experimental Psychologists in 1996. Grossberg received
his graduate training at Stanford University and Rockefeller
University, and was a Professor at MIT before assuming his
present position at Boston University.
|
