Single-Iteration Threshold Hamming Networks

Abstract

We analyze in detail the performance of a Hamming network clas(cid:173) sifying inputs that are distorted versions of one of its m stored memory patterns. The activation function of the memory neurons in the original Hamming network is replaced by a simple threshold function. The resulting Threshold Hamming Network (THN) cor(cid:173) rectly classifies the input pattern, with probability approaching 1, using only O(mln m) connections, in a single iteration. The THN drastically reduces the time and space complexity of Hamming Net(cid:173) work classifiers.

Cite

Text

Meilijson et al. "Single-Iteration Threshold Hamming Networks." Neural Information Processing Systems, 1992.

Markdown

[Meilijson et al. "Single-Iteration Threshold Hamming Networks." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/meilijson1992neurips-singleiteration/)

BibTeX

@inproceedings{meilijson1992neurips-singleiteration,
  title     = {{Single-Iteration Threshold Hamming Networks}},
  author    = {Meilijson, Isaac and Ruppin, Eytan and Sipper, Moshe},
  booktitle = {Neural Information Processing Systems},
  year      = {1992},
  pages     = {564-571},
  url       = {https://mlanthology.org/neurips/1992/meilijson1992neurips-singleiteration/}
}