An Improved Algorithm of Neural Networks with Cubic Spline Weight Function

摘要：

The paper proposes an improved Neural Networks construction with Cubic Spline Weight Function and its algorithm for the characteristic of the poor extending ability of the Neural Networks with Cubic SplineWeight Function. The Weight Function is divided into two parts by the improved algorithm. The Weight Function is trained by the three Cubic SplineWeight Function of the original algorithm and the constant coefficient of theWeight Function is trained by the grad dropping method. Because the new algorithm combines the merits of the Cubic Spline Weight Function Neural Networks with the merits of the traditional Neural Networks, the problems of the traditional dropping algorithm, such as the local minimum, slow convergence rate and initial value sensitivity, are not existed and the extending ability is better. The results of the simulation shows that compared to the traditional algorithm, the algorithm has high precision, fast speed and the extending ability remarkably improved compared to the unimproved algorithm.

关键词： Neural Networks with Cubic SplineWeight Function Weight Function Liner Neural Networks Extending Ability

作者: Liu Keyuan Li Haibin He Yan Duan Zhixin

作者单位: Science College, Inner Mongolia University of Technology, Hohhot 010051, China

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: 2673-2677

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）