Neural Computation, Vol 8, 1711-1729, Copyright © 1996 by The MIT Press
Neural correlation via random connections
J Chover
Department of Mathematics, University of Wisconsin-Madison 53706, USA.
A simple neural network is studied, which has sparse, random, plastic,
excitatory connections and also feedback loops between sensory cells and
correlator cells. Time is limited to several discrete instants, where
firing is synchronous. For parameter values within biological ranges, the
system exhibits a capacity for associative recall, with a controlled amount
of extraneous firing, following Hebb-like synaptic changes.
