具时滞的联想记忆神经网络模型动力学性质

为了研究时滞对联想记忆神经网络模型动力学行为的影响,考虑了一个含有n+1个神经元的具多时滞的双向联想记忆神经网络模型.以模型中的时滞为参数,利用泛函微分方程的全局Hopf分支存在定理和常微分方程的Bendixson周期解不存在定理,给出该模型非平凡周期解全局存在的充分条件,为双向联想记忆神经网络的设计和应用提供了重要的理论依据.最后利用一个例子进行了数值仿真,仿真结果表明了结论的有效性.

Dynamical quality in bidirectional associative memory neural network model

In order to study for the effect of delay in dynamic behavior of associative memory neural network model, an n+1-dimensional bidirectional associative memory (BAM) neural network model with multi-delay was considered. Sufficient conditions for nontrivial periodic solution were met by the model by taking delay as a parameter, using the global Hopf bifurcation existence theorem of the functional differential equation and the Bendixson non-existent theorem of the ordinary differential equation. These provide important theoretical basis for the design and application of BAM neural network. Finally, numerical simulations were carried out and results show that the proposed conclusion is effective.