%0 Journal Article
%T A Fast Learning Algorithm of Global Convergence for BP-Neural Network
一种快速且全局收敛的BP神经网络学习算法
%A HU Jie
%A
胡洁
%J 系统科学与数学
%D 2010
%I
%X There are many successful applications of back-propagation (BP) for training multi-layer neural networks. However, it has many shortcomings. Learning often takes long time to converge, and it may fall into local minima. In this paper, a fastlearning algorithm of global convergence for BP neural network is presented. Furthermore, the convergence of the optimization algorithm is analyzed in detail. A simulation example shows that the proposed algorithm is more efficient and accurate than the standard BP method.
%K Global convergence
%K optimization
%K learning algorithm
%K BP neural network
全局收敛
%K 优化
%K 学习算法
%K BP
%K 神经网络.
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=6E709DC38FA1D09A4B578DD0906875B5B44D4D294832BB8E&cid=37F46C35E03B4B86&jid=0CD45CC5E994895A7F41A783D4235EC2&aid=7D97701D711C51F8BF9ABF33E20C83F4&yid=140ECF96957D60B2&vid=340AC2BF8E7AB4FD&iid=94C357A881DFC066&sid=1A0C7C60D40EFD74&eid=44E78A5D1B37D836&journal_id=1000-0577&journal_name=系统科学与数学&referenced_num=0&reference_num=15