摘要
提出了一个新的高阶双向联想记忆模型.它推广了由Tai及Jeng所提出的高阶双向联想记忆模型HOBAM(higher-orderbidirectionalassociativememory)及修正的具有内连接的双向联想记忆模型MIBAM(modifiedintraconnectedbidirectionalassociativememory),通过定义能量函数,证明了新模型在同步与异步更新方式下的稳定性,从而能够保证所有被训练模式对成为该模型的渐近稳定点.借助统计分析原理,估计了所提模型的存储容量.计算机模拟证实此模型不仅具有较高的存储容量,而且还具有较好的纠错能力.
In this paper, a new higher order bidirectional associative memory model is presented. It is an extension of Tai's HOBAM(higher order bidirectional associative memory) and Jeng's MIBAM(modified intraconnected BAM). The stability of the new model, in synchronous and asynchronous updating modes, is proven by defining an energy function such that it can ensure all the training pattern pairs to become its asymptotically stable points. Using statistical analysis principle, the storage capacity of the proposed model is estimated. The computer simulations show that this model has not only higher storage capacity but also better error correcting capability.
出处
《软件学报》
EI
CSCD
北大核心
1998年第11期814-819,共6页
Journal of Software
基金
国家自然科学基金
关键词
联想记忆
神经网络
高阶非线性
存储容量
BAM(bidirectional associative memories), neural networks, higher order nonlinearity, storage capacity.