Convergence of Online gradient algorithm with Stochastic inputs for Pi-Sigma neural networks
点击次数:
论文类型:会议论文
发表时间:2007-04-01
收录刊物:EI、CPCI-S、Scopus
页面范围:564-+
关键字:Pi-Sigma neural network; online gradient algorithm; stochastic input; convergence; monotonicity
摘要:An online gradient method is presented and discussed for Pi-Sigma neural networks with stochastic inputs. The error function is proved to be monotone in the training process, and the gradient of the error function tends to zero if the weights sequence is uniformly bounded. Furthermore, after adding a moderate condition, the weights sequence itself is also proved to be convergent.
发表时间:2007-04-01