Euler Neural Network with itsWeight-Direct-Determination and Structure-Automatic-Determination Algorithms

摘要：

To overcome the intrinsic weaknesses of conventional back-propagation (BP) neural networks, a novel type of feed-forward neural network is constructed in this paper, which adopts a three-layer structure but with the hidden-layer neurons activated by a group of Euler polynomials. A weightsdirect- determination (WDD) method is thus able to be derived for it, which obtains the optimal weights of the neural network directly (i.e., just in one step). Furthermore, a structureautomatic- determination (SAD) algorithm is presented to determine the optimal number of hidden-layer neurons of the Euler neural network (ENN). Computer-simulations substantiate the ef.cacy of such a Euler neural network with its WDD and SAD algorithms.

关键词： Euler polynomials Arti?cial neural networks Iteration Matrix pseudoinverse Weights-direct-determination Structure-automatic-determination

作者: Yunong Zhang Lingfeng Li Yiwen Yang Gongqin Ruan

作者单位: School of Information Science and Technology, Guangzhou 510275, China School of Software Sun Yat-Sen University, Guangzhou 510275, China

会议类型: 国际会议

会议名称: 2009 Ninth International Conference on Hybrid Intelligent Systems(第九届混合智能系统国际会议 HIS 2009)

会议地点: 沈阳

会议语种:英文

页码: 1-6

在线出版日期: 2009-08-12（万方平台首次上网日期，不代表论文的发表时间）