A learning algorithm of artificial neural network based on genetic algorithm

In order to get over the insufficiency of BP algorithm, a new learning algorithm of artificial neural network based on genetic algorithm is given. The results of emulation show: using genetic algorithm optimize weight and threshold of artificial neural network, not only can be putted into practice, but has very appealing advantages. The algorithm can get over the insufficiency of BP algorithm, such as: liable to get into local minimum, slow speed in training, derivative error function required, limited to network architecture.