基于约束区域的连续时间联想记忆神经网络

传统的联想记忆神经网络模型是根据联想记忆点设计权值。文中提出一种根据联想记忆点设计基于约束区域的神经网络模型，它保证了渐近稳定的平衡点集与样要点集相同，不渐近稳定的平衡点恰为实际的拒识状态，并且吸引域分布合理。它具有学习和遗忘能力，还具有记忆容量大和电路可实现优点，是理想的联想记忆器。

THE CONTINUOUS NEURAL NETWORK BASED ON THE CONSTRAINT DOMAIN FOR ASSOCIATIVE MEMORY

The traditional neural network for associative memory is to design interconnection matrix according to prototype patterns. This paper presents a neural network based on the constraint domain according to prototype patterns. It guarantees that the set of prototype patterns is the same as the set of asymptotically stable equilibrium points,an equilibrium point which is not asymptotically stable is just the state that can not be recognized. Furthermore, the basin of attraction of each desired memory pattern is distributed reasonably. The proposed network also has the capability of learning and forgetting, it also has privileges of high capacity and easy implementation. It is the idea model for associative memory.