English

Associative Memories Based on Multiple-Valued Sparse Clustered Networks

Neural and Evolutionary Computing 2016-11-18 v1

Abstract

Associative memories are structures that store data patterns and retrieve them given partial inputs. Sparse Clustered Networks (SCNs) are recently-introduced binary-weighted associative memories that significantly improve the storage and retrieval capabilities over the prior state-of-the art. However, deleting or updating the data patterns result in a significant increase in the data retrieval error probability. In this paper, we propose an algorithm to address this problem by incorporating multiple-valued weights for the interconnections used in the network. The proposed algorithm lowers the error rate by an order of magnitude for our sample network with 60% deleted contents. We then investigate the advantages of the proposed algorithm for hardware implementations.

Keywords

Cite

@article{arxiv.1402.0808,
  title  = {Associative Memories Based on Multiple-Valued Sparse Clustered Networks},
  author = {Hooman Jarollahi and Naoya Onizawa and Takahiro Hanyu and Warren J. Gross},
  journal= {arXiv preprint arXiv:1402.0808},
  year   = {2016}
}

Comments

6 pages, Accepted in IEEE ISMVL 2014 conference

R2 v1 2026-06-22T03:01:13.719Z