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

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 eq...

Full description

Saved in:
Bibliographic Details
Published in:Chinese physics B 2015-10, Vol.24 (12)
Main Authors: Huang, Yu-Jiao, Hu, Hai-Gen
Format: Article
Language:English
Subjects:
complex-valued recurrent neural network
delay
discontinuous real-imaginary-type activation function
multistability
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1674-1056
DOI:10.1088/1674-1056/24/12/120701