摘要
详细阐述了BP神经网络的拆分和组装方法,证明了它的正确性,并采用该方法来构造成一个学习结果达到均方根误差全局最小点的BP神经网络。该方法在有效克服局部极小点这一问题上具有普遍意义。
A solution named divide-assemble by deducing the size of BP neural network to overcome entering the local best point is introduced. The dividing process is realized by dividing a big BP neural network into several small ones, each of which can carry out study alone. Thereafter, they can be assembled to become the quondam big BP neural work. This approach is analyzed in detail with an example.
出处
《武汉理工大学学报（信息与管理工程版）》
CAS
2003年第5期13-16,共4页
Journal of Wuhan University of Technology：Information & Management Engineering
关键词
神经网络
神经网络的拆分
神经网络的组装
neural network
division of neural network
assemble of neural network
