An ANN Model of Optimizing Activation Functions Based on Constructive Algorithm and GP

摘要：

The importance of the activation functions in ANN is emphasized. A new ANN modeling method is proposed based on constructive algorithm and GP. This method can be used to realize the automatic optimization of the ANNs net structure and the activation functions. As a result, the ANNs constructure and generalization capability is greatly improved, its characteristic is better than the M-P feed forword neural network. This improvement is verified experimentally.

关键词： ANN constructive algorithm GP Activation functions

作者: Zhang Sheng Shang Xiuyu Wang Wei

作者单位: College of Mathematics, Physics and Information Engineering Zhejiang Normal University Jinhua, China College of Education Nanjing Normal University Nanjing China

会议类型: 国际会议

会议名称: The 2010 International Conference on Computer Application and System Modeling(2010计算机应用与系统建模国际会议 ICCASM 2010)

会议地点: 太原

会议语种:英文

页码: 420-424

在线出版日期: 2010-10-22（万方平台首次上网日期，不代表论文的发表时间）