摘要
本文从信噪比分析的角度对递归相关联想记忆(RCAM)模型中的非线性函数如何影响其性能的问题进行了研究,给出了一新的非线性函数。理论分析及仿真实验皆表明本文的模型有着更好的记忆性能。
This paper addresses the effect of nonlinearity of RCAM on its recall performance with the help of signal-to-noise analysis and presents a new nonlinear function. Theoretical analysis and computer simulations show that the presented memory model offers more satisfactory performance.
基金
国家攀登计划认知科学(神经网络)重大关键项目资助课题
关键词
联想记忆器
神经网络
容量
纠错能力
Associative memory, Neural network, Capacity, Error-correcting capability
