A New Improved CMAC Neural Network

摘要：

In order to accelerate the learning speed of the conventional CMAC, an Improved Credit Assigned CMAC (ICA-CMAC) is presented in this paper. And then the proposed ICA-CMAC is applied to approaching two objective functions. Simulation results show that the ICA-CMAC has faster learning speed. In addition, the paper discussed different performances of ICA-CMAC influenced by different learning rates. It was found that the ICA-CMAC with a learning rate less than 1 has a better learning performance, which might be useful in selecting an appropriate learning rate.

关键词： ICA-CMAC online learning credibility learning rate

作者: Yingqi Ge Xiaoping Luo Pengying Du

作者单位: China Jiliang University, Hangzhou, China, 310018 Zhejiang University City College Key Laboratory of Zhejiang University City College Key Laboratory of Intelligent Systems, Hangzhou, China, 310015 Zhejiang University City College, Hangzhou, China, 310015

会议类型: 国际会议

会议名称: The 22nd China Control and Decision Conference(2010年中国控制与决策会议)

会议地点: 徐州

会议语种:英文

页码: 3271-3274

在线出版日期: 2010-05-26（万方平台首次上网日期，不代表论文的发表时间）