反向传播算法的最大缺陷之一是容易陷入局部极小点.为此,我们在基因遗传算法(GA)原理的基础上,增加了区域变化这一重要环节,设计出一种新的启发式遗传操作算法,并将它用于多层神经网络的学习过程.实例结果表明用此算法能快速得到最佳权值分布. Back propagation algorithm is one of the biggest flaws is easy to fall into the local minimum.To this end, we based on the principle of genetic algorithms (GA), an increase of regional changes in this important part of the design of a new heuristic Genetic algorithm and apply it to the learning process of multi-layer neural network.Example results show that this algorithm can get the best weight distribution quickly.