基于非线性内电位构造函数的抗伪状态联想记忆  

Associative Memory with Anti-spurious-state Based on Nonlinear Function Constitution

作　　者：严晨[1] 夏旻 王直杰[1] 

机构地区：[1]东华大学信息科学与技术学院自动化系,上海201620

出　　处：《系统仿真学报》2009年第4期1040-1042,1046,共4页Journal of System Simulation

摘　　要：针对传统Hopfield神经网络在联想记忆中存在的大量伪状态,设计出一种以非线性内电位函数构造为核心的抗伪状态方案,以取代传统的Hebb规则及其外积法,建立了一种抗伪状态的联想记忆网络(ASS-SSNN),并通过吸引域的变化研究抗伪状态方案的正确性和有效性。仿真结果表明:ASS-SSNN比采用传统Hebb规则及其外积法的Hopfield联想记忆网络(HNN)在容错性上更优,记忆状态的吸引域明显增大,存储容量也有所增加。Nonlinear function constitution, against spurious state for Hopfield neural network was proposed. Ascribing to the nonlinear function for local field, the conventional Hebbian learning rule with linear outer product method can be improved. Therefore, the anti-spurious-state neural network with static synapses （ASS-SSNN） was proposed. Simulation results show that the methods can effectively increase the ability of error tolerance; furthermore, associative memory of neural network with this new method can both enlarge attractive basin and increase storage capacity.

关 键 词：HOPFIELD神经网络 联想记忆 伪状态 非线性内电位 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]