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

作　　者：黄玉娇 汪晓妍 龙海霞 杨旭华 

机构地区：[1]College of Computer Science and Technology,Zhejiang University of Technology

出　　处：《Chinese Physics B》2016年第12期194-201,共8页中国物理B（英文版）

基　　金：Project supported by the National Natural Science Foundation of China(Grant Nos.61503338,61573316,61374152,and 11302195);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.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 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]