ML Anthology

Minimal Feedforward Parity Networks Using Threshold Gates

Hon-Kwok Fung, Leong Kwan Li
NeCo 2001 pp. 319-326
doi:10.1162/089976601300014556 /neco/2001/fung2001neco-minimal/

Abstract

This article presents preliminary research on the general problem of reducing the number of neurons needed in a neural network so that the network can perform a specific recognition task. We consider a single-hidden-layer feedforward network in which only McCulloch-Pitts units are employed in the hidden layer. We show that if only interconnections between adjacent layers are allowed, the minimum size of the hidden layer required to solve the n-bit parity problem is n when n ≤ 4.

PDF NeCo Semantic Scholar

Cite

Text

Fung and Li. "Minimal Feedforward Parity Networks Using Threshold Gates." Neural Computation, 2001. doi:10.1162/089976601300014556

Markdown

[Fung and Li. "Minimal Feedforward Parity Networks Using Threshold Gates." Neural Computation, 2001.](https://mlanthology.org/neco/2001/fung2001neco-minimal/) doi:10.1162/089976601300014556

BibTeX

@article{fung2001neco-minimal,
  title     = {{Minimal Feedforward Parity Networks Using Threshold Gates}},
  author    = {Fung, Hon-Kwok and Li, Leong Kwan},
  journal   = {Neural Computation},
  year      = {2001},
  pages     = {319-326},
  doi       = {10.1162/089976601300014556},
  volume    = {13},
  url       = {https://mlanthology.org/neco/2001/fung2001neco-minimal/}
}