一种自适应遗传算法对Hopfield网络权值的优化

Optimization of Hopfield Network Weights with a Adaptive Genetic Algorithm

针对Hopfield网络在求解优化问题中学习效率低,收敛速度慢,容易陷入局部最优等缺点和不足,把遗传算法同Hopfield网络结合起来,形成进化神经网络,对网络权值进行优化,并且通过对算法的讨论,说明该算法的有效性。

In order to overcome the shortcomings of the Hopfield neural networks, such as low efficiency of study, slow speed of convergence, easy to be trapped into local optimums, etc., an evolutionary neural network is studied for the optimization of weights. The feasibility of the algorithm is illustrated based on some discussions.