Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

November 15, 1996, Vol. 8, No. 8, Pages 1711-1729
(doi: 10.1162/neco.1996.8.8.1711)
© 1996 Massachusetts Institute of Technology
Neural Correlation via Random Connections
Article PDF (971.64 KB)
Abstract

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.