计算机应用研究2012，Vol.29Issue(11)：4113-4116,4151,5.DOI:10.3969/j.issn.1001-3695.2012.11.028
多输入Sigmoid激励函数神经网络权值与结构确定法
Weights and structure determination method of multiple-input Sigmoid activation function neural network
摘要
Abstract
In order to overcome the inherent drawbacks of the BP neural network as well as its learning algorithms, this paper proposed a two-stage automatic search and determination method for optimal structure, which was based on the pseudoinverse-type weights direct determination (WDD) method. Taking function approximation for example, numerical experiment results demonstrate the proposed two-stage algorithm is effective and timesaving. They further show that the neural network has relatively excellent performance of approximation (i. e. , training and testing) on multivariate functions.关键词
BP神经网络/多输入/Sigmoid激励函数/权值直接确定法/双阶段结构自确定法Key words
BP neural network/ multiple-input/ Sigmoid activation function/ weights direct determination method/ two-stage structure automatic-determination method分类
信息技术与安全科学引用本文复制引用
张雨浓,曲璐,陈俊维,刘锦荣,郭东生..多输入Sigmoid激励函数神经网络权值与结构确定法[J].计算机应用研究,2012,29(11):4113-4116,4151,5.基金项目
国家自然科学基金资助项目(61075121) （61075121）
国家教育部高等学校博士学科点专项科研基金博导类课题(20100171110045) （20100171110045）
