A Multilayer RBF Network and its Supervised Learning

摘要：

In this paper a general form of multilayer RBF networks is introduced. A complete supervised training rules for parameters are also presented. To achieve global convergence we apply a global optimazation algorithm called magic-brush method. This network is then generalized to a pyramid network. Simulations shown higher representation and generalization capability of the proposed networks comparing with the RBF and multilayer networks with sigmoid activation functions.

作者: Jinhui Chao Miho Hoshino Tasuku Kitamura Takeshi Masuda

作者单位: Dept. of Electrical, Electronic and Communication Eng. Chuo University,1-13-27 Kasuga, Bunkyo-ku, Tokyo, 112-6551, Japan

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: 1404-1409

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）