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

Neural Computation

February 15, 1996, Vol. 8, No. 2, Pages 319-339
(doi: 10.1162/neco.1996.8.2.319)
© 1996 Massachusetts Institute of Technology
Binary-Oscillator Networks: Bridging a Gap between Experimental and Abstract Modeling of Neural Networks
Article PDF (898.67 KB)
Abstract

This paper proposes a simplified oscillator model, called binary-oscillator, and develops a class of neural network models having binary-oscillators as basic units. The binary-oscillator has a binary dynamic variable v = ±1 modeling the “membrane potential” of a neuron, and due to the presence of a “slow current” (as in a classical relaxation-oscillator) it can oscillate between two states. The purpose of the simplification is to enable abstract algorithmic study on the dynamics of oscillator networks. A binary-oscillator network is formally analogous to a system of stochastic binary spins (atomic magnets) in statistical mechanics.