Some Results on Convergent Unlearning Algorithm

Abstract

In this paper we consider probabilities of different asymptotics of convergent unlearning algorithm for the Hopfield-type neural net(cid:173) work (Plakhov & Semenov, 1994) treating the case of unbiased random patterns. We show also that failed unlearning results in total memory breakdown.

Cite

Text

Semenov and Shuvalova. "Some Results on Convergent Unlearning Algorithm." Neural Information Processing Systems, 1995.

Markdown

[Semenov and Shuvalova. "Some Results on Convergent Unlearning Algorithm." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/semenov1995neurips-some/)

BibTeX

@inproceedings{semenov1995neurips-some,
  title     = {{Some Results on Convergent Unlearning Algorithm}},
  author    = {Semenov, Serguei A. and Shuvalova, Irina B.},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {358-364},
  url       = {https://mlanthology.org/neurips/1995/semenov1995neurips-some/}
}