%0 Journal Article
%T Evolutionary Pseudo-Relaxation Learning Algorithm for Bidirectional Associative Memory
%A Sheng-Zhi Du
%A Zeng-Qiang Chen
%A Zhu-Zhi Yuan
%A <br>Sheng-Zhi Du
%A Zeng-Qiang Chen
%A and Zhu-Zhi Yuan
%J 计算机科学技术学报
%D 2005
%I 
%X This paper analyzes the sensitivity to noise in BAM (Bidirectional Associative Memory), and then proves the noise immunity of BAM relates not only to the minimum absolute value of net inputs (MAV) but also to the variance of weights associated with synapse connections. In fact, it is a positive monotonically increasing function of the quotient of MAV divided by the variance of weights. Besides, the performance of pseudo-relaxation method depends on learning parameters (λ and ξ), but the relation of them is not linear. So it is hard to find a best combination of λ and ξ which leads to the best BAM performance. And it is obvious that pseudo-relaxation is a kind of local optimization method, so it cannot guarantee to get the global optimal solution. In this paper, a novel learning algorithm EPRBAM (evolutionary psendo-relaxation learning algorithm for bidirectional association memory) employing genetic algorithm and pseudo-relaxation method is proposed to get feasible solution of BAM weight matrix. This algorithm uses the quotient as the fitness of each individual and employs pseudo-relaxation method to adjust individual solution when it does not satisfy constraining condition any more after genetic operation. Experimental results show this algorithm improves noise immunity of BAM greatly. At the same time, EPRBAM does not depend on learning parameters and can get global optimal solution. Supported by the National Natural Science Foundation of China (Grant No.60374037)
%K genetic algorithm
%K pseudo-relaxation method
%K associative memory
%K neural network
%K noise immunity
%K digital pattern<br>存储器
%K 数据存储
%K 存储容量
%K 计算机
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=F57FEF5FAEE544283F43708D560ABF1B&aid=726ACC619D0868A9EF255A4857772CD2&yid=2DD7160C83D0ACED&vid=A04140E723CB732E&iid=E158A972A605785F&sid=8966A0F1B07BE5EE&eid=CDC418F38C4BFD60&journal_id=1000-9000&journal_name=计算机科学技术学报&referenced_num=0&reference_num=23