中国物理B ›› 2016, Vol. 25 ›› Issue (12): 120701-120701.doi: 10.1088/1674-1056/25/12/120701

• GENERAL • 上一篇    下一篇

Synthesization of high-capacity auto-associative memories using complex-valued neural networks

Yu-Jiao Huang(黄玉娇), Xiao-Yan Wang(汪晓妍), Hai-Xia Long(龙海霞), Xu-Hua Yang(杨旭华)   

  1. College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China
  • 收稿日期:2016-05-18 修回日期:2016-07-15 出版日期:2016-12-05 发布日期:2016-12-05
  • 通讯作者: Yu-Jiao Huang E-mail:hyj0507@zjut.edu.cn
  • 基金资助:

    Project supported by the National Natural Science Foundation of China (Grant Nos. 61503338, 61573316, 61374152, and 11302195) and the Natural Science Foundation of Zhejiang Province, China (Grant No. LQ15F030005).

Synthesization of high-capacity auto-associative memories using complex-valued neural networks

Yu-Jiao Huang(黄玉娇), Xiao-Yan Wang(汪晓妍), Hai-Xia Long(龙海霞), Xu-Hua Yang(杨旭华)   

  1. College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China
  • Received:2016-05-18 Revised:2016-07-15 Online:2016-12-05 Published:2016-12-05
  • Contact: Yu-Jiao Huang E-mail:hyj0507@zjut.edu.cn
  • Supported by:

    Project supported by the National Natural Science Foundation of China (Grant Nos. 61503338, 61573316, 61374152, and 11302195) and the Natural Science Foundation of Zhejiang Province, China (Grant No. LQ15F030005).

摘要:

In this paper, a novel design procedure is proposed for synthesizing high-capacity auto-associative memories based on complex-valued neural networks with real-imaginary-type activation functions and constant delays. Stability criteria dependent on external inputs of neural networks are derived. The designed networks can retrieve the stored patterns by external inputs rather than initial conditions. The derivation can memorize the desired patterns with lower-dimensional neural networks than real-valued neural networks, and eliminate spurious equilibria of complex-valued neural networks. One numerical example is provided to show the effectiveness and superiority of the presented results.

关键词: associative memory, complex-valued neural network, real-imaginary-type activation function, external input

Abstract:

In this paper, a novel design procedure is proposed for synthesizing high-capacity auto-associative memories based on complex-valued neural networks with real-imaginary-type activation functions and constant delays. Stability criteria dependent on external inputs of neural networks are derived. The designed networks can retrieve the stored patterns by external inputs rather than initial conditions. The derivation can memorize the desired patterns with lower-dimensional neural networks than real-valued neural networks, and eliminate spurious equilibria of complex-valued neural networks. One numerical example is provided to show the effectiveness and superiority of the presented results.

Key words: associative memory, complex-valued neural network, real-imaginary-type activation function, external input

中图分类号:  (Neural networks, fuzzy logic, artificial intelligence)

  • 07.05.Mh
02.30.Ks (Delay and functional equations)