期刊
NEURAL COMPUTING & APPLICATIONS
卷 27, 期 4, 页码 837-844出版社
SPRINGER LONDON LTD
DOI: 10.1007/s00521-015-1899-7
关键词
Small-world; Memristor; Weight salience; Digit recognition
资金
- Program for New Century Excellent Talents in University [[2013]47]
- National Natural Science Foundation of China [61372139, 61101233, 60972155]
- Ministry of Education of China [z2011148]
- Technology Foundation for Selected Overseas Chinese Scholars, Ministry of Personnel in China [2012-186]
- University Excellent Talents Supporting Foundations in of Chongqing [2011-65]
- University Key Teacher Supporting Foundations of Chongqing [2011-65]
- Fundamental Research Funds for the Central Universities [XDJK2014A009, XDJK2013B011]
- Direct For Computer & Info Scie & Enginr
- Division of Computing and Communication Foundations [1337198] Funding Source: National Science Foundation
- Directorate For Engineering
- Div Of Electrical, Commun & Cyber Sys [1311747] Funding Source: National Science Foundation
A novel systematic design of associative memory networks is addressed in this paper, by incorporating both the biological small-world effect and the recently acclaimed memristor into the conventional Hopfield neural network. More specifically, the original fully connected Hopfield network is diluted by considering the small-world effect, based on a preferential connection removal criteria, i.e., weight salience priority. The generated sparse network exhibits comparable performance in associative memory but with much less connections. Furthermore, a hardware implementation scheme of the small-world Hopfield network is proposed using the experimental threshold adaptive memristor (TEAM) synaptic-based circuits. Finally, performance of the proposed network is validated by illustrative examples of digit recognition.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据