ML Anthology

Parallel Activation of Memories in an Oscillatory Neural Network

David Horn, Marius Usher
NeCo 1991 pp. 31-43
doi:10.1162/NECO.1991.3.1.31 /neco/1991/horn1991neco-parallel/

Abstract

We describe a feedback neural network whose elements possess dynamic thresholds. This network has an oscillatory mode that we investigate by measuring the activities of memory patterns as functions of time. We observe spontaneous and induced transitions between the different oscillating memories. Moreover, the network exhibits pattern segmentation, by oscillating between different memories that are included as a mixture in a constant input. The efficiency of pattern segmentation decreases strongly as the number of the input memories is increased. Using oscillatory inputs we observe resonance behavior.

NeCo Semantic Scholar

Cite

Text

Horn and Usher. "Parallel Activation of Memories in an Oscillatory Neural Network." Neural Computation, 1991. doi:10.1162/NECO.1991.3.1.31

Markdown

[Horn and Usher. "Parallel Activation of Memories in an Oscillatory Neural Network." Neural Computation, 1991.](https://mlanthology.org/neco/1991/horn1991neco-parallel/) doi:10.1162/NECO.1991.3.1.31

BibTeX

@article{horn1991neco-parallel,
  title     = {{Parallel Activation of Memories in an Oscillatory Neural Network}},
  author    = {Horn, David and Usher, Marius},
  journal   = {Neural Computation},
  year      = {1991},
  pages     = {31-43},
  doi       = {10.1162/NECO.1991.3.1.31},
  volume    = {3},
  url       = {https://mlanthology.org/neco/1991/horn1991neco-parallel/}
}