联合优化的BP神经网络模型的应用研究

BP算法因收敛速度慢、易于陷入局部极小值等缺点，使得对于较大的搜索空间、多峰值和不可微函数常常不能搜索到全局极小点，这些制约了BP网络在各个领域中的应用。本文通过对学习系数、神经元的激励函数及误差函数的联合优化，在一定程度上避免了学习中的局部极小问题，提高了学习效率，改进了网络的性能。

Application study of joint optimization models of BP network

BP algorithm has weaknesses such as slow convergent speed and easy getting into local minimum, insurable to find global extreme value point for multi-modal and non-differential function in larger searching zone, which restrict neural network's application in every field. In this thesis, The Joint Optimization of learning-coefficient, activation function and error function. Experiment results show that the modified BP arithmetic not only has high efficiency, but also can avoid from getting into local minimum in some degree and modified the capacity of network.