The Behavior of Forgetting Learning in Bidrectional Associative Memory

Abstract

Forgetting learning is an incremental learning rule in associative memories. With it, the recent learning items can be encoded, and the old learning items will be forgotten. In this article, we analyze the storage behavior of bidirectional associative memory (BAM) under the forgetting learning. That is, “Can the most recent k learning item be stored as a fixed point?” Also, we discuss how to choose the forgetting constant in the forgetting learning such that the BAM can correctly store as many as possible of the most recent learning items. Simulation is provided to verify the theoretical analysis.

Cite

Text

Leung and Chan. "The Behavior of Forgetting Learning in Bidrectional Associative Memory." Neural Computation, 1997. doi:10.1162/NECO.1997.9.2.385

Markdown

[Leung and Chan. "The Behavior of Forgetting Learning in Bidrectional Associative Memory." Neural Computation, 1997.](https://mlanthology.org/neco/1997/leung1997neco-behavior/) doi:10.1162/NECO.1997.9.2.385

BibTeX

@article{leung1997neco-behavior,
  title     = {{The Behavior of Forgetting Learning in Bidrectional Associative Memory}},
  author    = {Leung, Andrew Chi-Sing and Chan, Lai-Wan},
  journal   = {Neural Computation},
  year      = {1997},
  pages     = {385-401},
  doi       = {10.1162/NECO.1997.9.2.385},
  volume    = {9},
  url       = {https://mlanthology.org/neco/1997/leung1997neco-behavior/}
}