中国物理B ›› 2015, Vol. 24 ›› Issue (12): 120701-120701.doi: 10.1088/1674-1056/24/12/120701

• GENERAL • 上一篇    下一篇

Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions

黄玉娇, 胡海根   

  1. College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China
  • 收稿日期:2015-05-12 修回日期:2015-06-27 出版日期:2015-12-05 发布日期:2015-12-05
  • 通讯作者: Huang Yu-Jiao E-mail:hyj0507@zjut.edu.cn
  • 基金资助:

    Project supported by the National Natural Science Foundation of China (Grant Nos. 61374094 and 61503338) and the Natural Science Foundation of Zhejiang Province, China (Grant No. LQ15F030005).

Multistability of delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions

Huang Yu-Jiao (黄玉娇), Hu Hai-Gen (胡海根)   

  1. College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310023, China
  • Received:2015-05-12 Revised:2015-06-27 Online:2015-12-05 Published:2015-12-05
  • Contact: Huang Yu-Jiao E-mail:hyj0507@zjut.edu.cn
  • Supported by:

    Project supported by the National Natural Science Foundation of China (Grant Nos. 61374094 and 61503338) and the Natural Science Foundation of Zhejiang Province, China (Grant No. LQ15F030005).

摘要:

In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.

关键词: complex-valued recurrent neural network, discontinuous real-imaginary-type activation function, multistability, delay

Abstract:

In this paper, the multistability issue is discussed for delayed complex-valued recurrent neural networks with discontinuous real-imaginary-type activation functions. Based on a fixed theorem and stability definition, sufficient criteria are established for the existence and stability of multiple equilibria of complex-valued recurrent neural networks. The number of stable equilibria is larger than that of real-valued recurrent neural networks, which can be used to achieve high-capacity associative memories. One numerical example is provided to show the effectiveness and superiority of the presented results.

Key words: complex-valued recurrent neural network, discontinuous real-imaginary-type activation function, multistability, delay

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

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