摘要
为克服和改进传统的BP算法的不足,发挥神经网络和遗传算法各自的优势,本文提出了一种基于遗传算法的人工神经网络二次训练方法。本方法将遗传算法应用于神经网络的权值训练中,并用神经网络二次训练得到最终结果,降低了计算时间,是一种比较有效的方法。
In order to overcome the lack of BP algorithm, Utilizing the advantage of Neural Network and genetic algorithm, a kind of two-times training method based on genetic algorithm is proposed. Genetic algorithm is applied in the weight training of neural network ,and using the two-times training method of the Neural Network come to the conclusion. The efficient method this paper proposed can reducing calculating time.
出处
《微电子学与计算机》
CSCD
北大核心
2005年第3期252-254,258,共4页
Microelectronics & Computer
关键词
BP算法
遗传算法
二次训练
人工神经网络
BP algorithm, Genetic algorithm, Two-times training, Neural network
