CONVERGENCE OF ONLINE GRADIENT METHOD WITH A PENALTY TERM FOR FEEDFORWARD NEURAL NETWORKS WITH STOCHASTIC INPUTS |
| |
作者姓名: | 邵红梅 吴微 李峰 |
| |
作者单位: | [1]DepartmentofAppliedMathematics,DalianUniversityofTechnology,Dalian116024,PRC. [2]DepartmentofAppliedMathematics,DalianUniversityofTechnology,Dalian116024,PRC. |
| |
基金项目: | Partly supported by the National Natural Science Foundation of China,and the Basic Research Program of the Committee of Science,Technology and Industry of National Defense of China. |
| |
摘 要: | Online gradient algorithm has been widely used as a learning algorithm for feedforward neural network training. In this paper, we prove a weak convergence theorem of an online gradient algorithm with a penalty term, assuming that the training examples are input in a stochastic way. The monotonicity of the error function in the iteration and the boundedness of the weight are both guaranteed. We also present a numerical experiment to support our results.
|
关 键 词: | 前馈神经网络系统 收敛 随机变量 单调性 有界性原理 在线梯度计算法 |
本文献已被 CNKI 维普 等数据库收录! |
|