Associative Memories Based on Multiple-Valued Sparse Clustered Networks
This addresses a specific bottleneck in associative memory systems, offering an incremental improvement for applications requiring dynamic data updates.
The paper tackled the problem of increased error probability when deleting or updating data patterns in Sparse Clustered Networks (SCNs) for associative memories, and the result was a proposed algorithm using multiple-valued weights that lowered the error rate by an order of magnitude for a sample network with 60% deleted contents.
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.