文献类型：期刊文献

英文题名：Convergence of Online Gradient Method with Momentum for BP Neural Network

作者：Pan, Chengyan[1]; Xie, Gang[1]

机构：[1] School of Science, East China University of Science and Technology, Shanghai, China

年份：2021

卷号：1802

期号：4

外文期刊名：IOP Conference Series: Earth and Environmental Science

收录：EI(收录号：20211310130008)

语种：英文

外文关键词：Backpropagation - Multilayer neural networks - Momentum - Network layers

摘要：The BP neural network, which uses the steepest descent method (gradient descent method) as the basic idea for learning, is often used to deal with approximation problems because of its strong nonlinear mapping ability. The gradient method with added momentum can improve the learning speed of BP neural network. We study the convergence of the online gradient method with momentum for two-layer BP neural network when the training samples are randomly arranged in each iteration. Choosing appropriate learning rates, and selecting momentum coefficients in an adaptive manner, we prove the weak and strong convergence theorems of the algorithm. ? Published under licence by IOP Publishing Ltd.