ML Anthology

Adding Recurrence to a Simple Feedforward Network Can Enable It to Perform Exclusive-or

Leslie S. Smith
NeCo 1998 pp. 277-280
doi:10.1162/089976698300017755 /neco/1998/smith1998neco-adding/

Abstract

A simple laterally inhibited recurrent network that implementse xclusive-or is demonstrated. The network consists of two mutually inhibitory units with logistic output function, each receiving one external input and each connected to a simple threshold output unit. The mutually inhibitory units settle into a point attractor. We investigate the range of steepness of the logistic and the range of inhibitory weights for which the network can perform exclusive-or.

NeCo Semantic Scholar

Cite

Text

Smith. "Adding Recurrence to a Simple Feedforward Network Can Enable It to Perform Exclusive-or." Neural Computation, 1998. doi:10.1162/089976698300017755

Markdown

[Smith. "Adding Recurrence to a Simple Feedforward Network Can Enable It to Perform Exclusive-or." Neural Computation, 1998.](https://mlanthology.org/neco/1998/smith1998neco-adding/) doi:10.1162/089976698300017755

BibTeX

@article{smith1998neco-adding,
  title     = {{Adding Recurrence to a Simple Feedforward Network Can Enable It to Perform Exclusive-or}},
  author    = {Smith, Leslie S.},
  journal   = {Neural Computation},
  year      = {1998},
  pages     = {277-280},
  doi       = {10.1162/089976698300017755},
  volume    = {10},
  url       = {https://mlanthology.org/neco/1998/smith1998neco-adding/}
}