arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1402.0808cs.NE
收藏

基于多值稀疏网络的联想记忆

Associative Memories Based on Multiple-Valued Sparse Clustered Networks

Hooman Jarollahi, Naoya Onizawa, Takahiro Hanyu, Warren J. Gross

摘要:

关联存储器是存储数据模式并在给定部分输入的情况下检索它们的结构。稀疏关联网络(SCN)是近年来提出的一种二进制加权关联存储器,其存储和检索能力大大优于现有技术,但删除或更新数据模式会导致数据检索错误概率的显著增加。在本文中,我们提出了一种算法来解决这个问题,将多值权重的互连网络中使用。该算法将出错率降低了一个数量级,我们的样本网络删除60%的内容。然后,我们调查的硬件实现所提出的算法的优点。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑