摘要
提出了一种混沌神经网络模型．通过引入暂态混沌和时变增益，该网络比Ｈｏｐｆｉｅｌｄ型网络具有更加丰富和更为灵活的动力学特性，从而具有更强的搜索全局最优解或近似全局最优解的能力．它可以用于求解各种复杂的优化问题．大量的数字模拟表明网络能较好地解决Ｈｏｐｆｉｅｌｄ型网络的局部极值问题．
By introducing transient chaos and time variant gain, the proposed chaotic neural network has richer and more flexible dynamics than Hopfield like neural networks only with point attractors, so that it can be expected to have higher ability of searching for globally optimal or near optimal solutions. It can be used to solving various complicated optimization problem and associative memories. A lot of simulations show that the network is hardly stuck into local minima.
出处
《东南大学学报（自然科学版）》
EI
CAS
CSCD
1998年第6期1-5,共5页
Journal of Southeast University：Natural Science Edition
基金
国家攀登计划
国家自然科学基金
