ML Anthology

Binary-Oscillator Networks: Bridging a Gap Between Experimental and Abstract Modeling of Neural Networks

Wei-Ping Wang
NeCo 1996 pp. 319-339
doi:10.1162/NECO.1996.8.2.319 /neco/1996/wang1996neco-binaryoscillator/

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.

NeCo Semantic Scholar

Cite

Text

Wang. "Binary-Oscillator Networks: Bridging a Gap Between Experimental and Abstract Modeling of Neural Networks." Neural Computation, 1996. doi:10.1162/NECO.1996.8.2.319

Markdown

[Wang. "Binary-Oscillator Networks: Bridging a Gap Between Experimental and Abstract Modeling of Neural Networks." Neural Computation, 1996.](https://mlanthology.org/neco/1996/wang1996neco-binaryoscillator/) doi:10.1162/NECO.1996.8.2.319

BibTeX

@article{wang1996neco-binaryoscillator,
  title     = {{Binary-Oscillator Networks: Bridging a Gap Between Experimental and Abstract Modeling of Neural Networks}},
  author    = {Wang, Wei-Ping},
  journal   = {Neural Computation},
  year      = {1996},
  pages     = {319-339},
  doi       = {10.1162/NECO.1996.8.2.319},
  volume    = {8},
  url       = {https://mlanthology.org/neco/1996/wang1996neco-binaryoscillator/}
}