Adaptive Resonance Theory 2002
<p class="default">03:10 PM, July 20, 2007
 
 
<b>Adaptive Resonance Theory</b> : paper by Gail and Steve:
 
This is their best summary of the work and is in
 <b>Mike Arbib, MIT Press: Handbook of Brain Theory and Neural Networks</b> 2nd ed. submit 1998; revised 2002.
 
 
ART
 
Principles derived from an analysis of experimental literatures in vision, speech, cortical
development, and reinforcement learning, including attentional blocking and cognitive-emotional
interactions, led to the introduction of adaptive resonance as a theory of human cognitive
information processing (Grossberg, 1976). The theory has evolved as a series of real - time neural
network models that perform unsupervised and supervised learning, pattern recognition, and
prediction (Duda, Hart, and Stork, 2001; Levine, 2000).
 
A central feature of all ART systems is a pattern matching process that compares an external
input with the internal memory of an active code. ART matching leads either to a  <i>resonant</i> state,
which persists long enough to permit learning, or to a parallel memory search. If the search ends at
an established code, the memory representation may either remain the same or incorporate new
information from matched portions of the current input. If the search ends at a new code, the
memory representation learns the current input. This  <i>match-based learning</i> process is the
foundation of ART code stability. Match-based learning allows memories to change only when
input from the external world is close enough to internal expectations, or when something
completely new occurs. This feature makes ART systems well suited to problems that require online
learning of large and evolving databases.</p>