改进的指数双向联想记忆模型及性能估计

提出了一个新的改进型指数双向联想记忆模型（ｉｍｐｒｏｖｅｄｅＢＡＭ，简称ＩｅＢＡＭ）．通过定义有界且随状态改变而下降的能量函数，证明了ＩｅＢＡＭ在状态的同、异步更新方式下的稳定性，一方面排除了Ｗａｎｇ的修正指数ＢＡＭ（ｍｏｄｉｆｉｅｄｅＢＡＭ，简称ＭｅＢＡＭ）和Ｊｅｎｇ的ｅＢＡＭ（ｅｘｐｏｎｅｎｔｉａｌＢＡＭ）的稳定性证明中所作的不合理假设；另一方面，放宽了对ＢＡＭ（ｂｉｄｉｒｅｃｔｉｏｎａｌａｓｓｏｃｉａｔｉｖｅｍｅｍｏｒｙ）的连续性假设的要求，并避免了补码问题．理论分析和计算机模拟结果表明。

A novel memristive neural network with hidden attractors and its circuitry implementation

Neural networks have been applied in various fields from signal processing, pattern recognition, associative memory to artifi- cial intelligence. Recently, nanoscale memristor has renewed interest in experimental realization of neural network. A neural network with a memristive synaptic weight is studied in this work. Dynamical properties of the proposed neural network are investigated through phase portraits, Poincar6 map, and Lyapunov exponents. Interestingly, the memristive neural network can generate hyperchaotic attractors without the presence of equilibrium points. Moreover, circuital implementation of such memristive neural network is presented to show its feasibility.