The way double polarity s function and LM algorithm combine with BP neural network is analyzed in the paper. The steps of new algorithm were given.
分析了双极性S型函数及LM算法与BP神经网络具体结合实现的方法,并给出了算法步骤。
A fuzzy neural network in t s model is constructed. Chaotic mechanism is introduced into the normal BP algorithm to train the weight parameters of the fuzzy neural networks.
出一种T - S模型的模糊神经网络,在通常BP算法的基础上,引进混沌机制来训练模糊神经网络的权值参数。
The imitation of computer proves that BP G S algorithm may decrease learning time in the whole. The effect is obvious especially when the error value is near to the optimal point.
文章最后的计算机仿真说明BPGS总体上可以减少学习的时间,尤其当误差值逼近最小点时效果明显。
应用推荐