Adaptive Structure of the Radial Basis Function Network Using Time-Frequency Localization

摘要：

In this paper, we propose the initial optimized structure of the Radial Basis Function Network which is more simple in the part of the structure and converges more faster than Neural Network with the analysis method using Time-Frequency Localization. When we construct the hidden node with the Radial Basis Function whose localization is similar with an approximation target function in the plane of the Time and Frequency, we make a good decision of the initial structure having an ability of approximation.

作者: Seong-Joo Kim Jae-Yong Seo Yong-Taek Kim Hyun-Chan Cho Hong-Tae Jeon

作者单位: School of Electrical and Electonic Eng. At Chung-Ang Univ School of Info. & Tech. Eng. at Korea University of Tech. & Edu

会议类型: 国际会议

会议名称: 8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)

会议地点: 上海

会议语种:英文

页码: 1533-1538

在线出版日期: 2001-11-14（万方平台首次上网日期，不代表论文的发表时间）