时滞Markov跳变BAM神经网络的鲁棒稳定性

针对一类具有Markov跳变参数的时滞双向联想记忆(BAM)神经网络,研究了其在系统参数不确定情况下的鲁棒稳定性.在不要求连接权矩阵的对称性和激励函数的可微性与单调性的情况下,通过构造适当的Lyapunov泛函得到了此类神经网络均方鲁棒稳定的充分条件.该条件考虑了时滞Markov跳变神经网络中参数的不确定性,改进了现有文献中的关于时滞Markov跳变神经网络的稳定性条件,所得结果以线性矩阵不等式(LMI)的形式给出.最后,通过实例仿真验证了所得结论的有效性.

Robust stability of delayed Markov jumping BAM neural networks

The robust stability for a class of delayed bidirectional associative memory neural networks with Markovian jumping parameters is investigated.Without assuming the differentiability and monotonicity of the activation functions and any symmetry of interconnection matrices,some sufficient conditions are proposed for the robust stability of the given neural networks by constructing suitable Lyapunov functional.The given results are derived in terms of linear matrix inequalities and improve the conclusion and the method existed in the literature.Finally,a numerical example is provided to illustrate the effectiveness of the theoretical results.