Convergence of Online Gradient Algorithm with Stochastic Inputs for Pi-Sigma Neural Networks
Xidai Kang, Yan Xiong, Chao Zhang, Wei Wu · 2007
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