Associative Memories Based on Multiple-Valued Sparse Clustered Networks
arXiv:1402.0808 · doi:10.1109/ISMVL.2014.44
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.
6 pages, Accepted in IEEE ISMVL 2014 conference