1. 西安交通大学系统工程研究所,西安,710049
2. 西安交通大学机械制造系统工程国家重点实验室,西安,710049
网络首发:2008-08-10,
纸质出版:2008
移动端阅览
韦晓亮 1, 冯祖仁 1, 2, 等. 利用最大似然准则的双向联想网络研究[J]. 西安交通大学学报, 2008,42(8):963-966+1043.
韦晓亮 1, 冯祖仁 1, 2, et al. Bidirectional Associative Memory Utilizing Maximum Likelihood[J]. 2008, 42(8): 963-966+1043.
针对现有双向联想网络(BAM)存在的存储容量小、抗干扰能力弱的缺点
提出了一种利用最大似然准则的BAM网络(MLBAM)及其训练算法. MLBAM网络采用双向网络结构建立了神经元的发放以及抑制模型
充分利用似然函数的特性以及网络的双向联想特性
很好地完成了自联想和异联想功能
并且准确计算出关联样本对之间的关联度
使MLBAM网络在随机环境中具有很强的抗噪能力.利用最速下降算法
给出了MLBAM网络的训练算法
根据训练权重的Hessian矩阵负定
判定算法能够获得全局最优解
从而证明了算法的收敛性.该训练算法能够训练出最优的连接权重和神经元阈值.通过2个典型实验验证了MLBAM网络的抗噪能力和联想能力
在存在1位随机噪声的情况下
该网络的联想正确率达到了100%.
A new learning rule and theoretical analysis of an extended bidirectional associative memory network(MLBAM)are presented by using the maximum likelihood criterion based on two well recognized and essential criteria
i.e.
the convergence of the learning rule
and the noise tolerance of the network. Traditional methods fail to distinguish highly closing patterns. However
this disadvantage is improved by using the newly developed method
since the maximum likelihood method is used to seek the best possible closing mapping of two patterns. Experiments are made to verify the validity and efficiency of the proposed method. The method displays excellent anti-noise property and MLBAM network exhibits association at a 100% accuracy under one-bit inversion which implies that 100% of the one-bit errors is corrected.
HECHT-NIELSEN R.Neurocomputing [M].Reading, Berkshire, UK:Addison Wesley Publishing Company, 1991.
KOSKO B.Adaptive bidirectional associative memories[J]. Applied Optics, 1987, 26(23): 4947-4960.
KOSKO B.Bidirectional associative memories[J]. IEEE Trans System,Man,and Cybernetics, 1988, 18(1): 49-60.
BARBER D, AGAKOV F.Correlated sequence learning in a network of spiking neurons using maximum likelihood, EDI-INF-RR-0149 [R]. Edinburgh, Scotland, UK: University of Edinburgh, School of Informatics, 2002.
WANG Y F,CRUZ J B Jr.MULLIGAN J H Jr. Two coding strategies for bidirectional associative memory [J]. IEEE Transactions on Neural Networks, 1990, 1(1):81-91.
WANG Zhengou.A bidirectional associative memory based on optimal linear associative memory [J]. IEEE Trans on Computers, 1996, 46(10): 1171-1179.
YUKIO K. Functional representation of recalling process and memory capacity in associative memory [C]∥IEEE-INNS-ENNS International Joint Conference on Neural Networks.Piscataway,NJ, USA:IEEE, 2000: 625-632.
CHARTIER S,BOUKADOUM M.A bidirectional heteroassociative memory for binary and grey-level patterns [J]. IEEE Transactions on Neural Networks, 2006, 17(2): 385-396.
0
浏览量
5
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621