Small-world Hopfield neural networks with weight salience priority and memristor synapses for digit recognition. Issue 4 (May 2016)

• Record Type: Journal Article
• Authors: Duan, Shukai; Dong, Zhekang; Hu, Xiaofang; Wang, Lidan; Li, Hai
• Is Part Of: Neural computing & applications. Volume 27:Issue 4(2016)
• Page Start: 837
• Page End: 844
• Publication Date: 2016-05
• Subjects: Small-world -- Memristor -- Weight salience -- Digit recognition; Neural networks (Computer science) -- Periodicals; Neural circuitry -- Periodicals; Artificial intelligence -- Periodicals; Neural Networks (Computer) -- Periodicals; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux nerveux -- Périodiques; Intelligence artificielle -- Périodiques; 006.32
• DOI: 10.1007/s00521-015-1899-7
• Languages: English
• ISSNs: 0941-0643

Abstract

Abstract 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.