Improved extreme learning machine for function approximation by encoding a priori information

被引：102

作者：

Han, Fei

Huang, De-Shuang

机构：

[1] Chinese Acad Sci, Hefei Inst Intelligent Machines, Intelligent Comp Lab, Hefei 230031, Anhui, Peoples R China

[2] Univ Sci & Technol China, Dept Automat, Hefei 230027, Peoples R China

来源：

NEUROCOMPUTING | 2006年 / 69卷 / 16-18期

基金：

中国国家自然科学基金;

关键词：

extreme learning machine; function approximation; the a priori information; generalization performance; convergence rate;

D O I：

10.1016/j.neucom.2006.02.013

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];

摘要：

In this letter, a class of improved extreme learning machines (ELM) encoding a priori information is proposed to obtain better generalization performance and much faster convergence rate for function approximation. According to Fourier series expansion theory, the hidden neurons activation functions in the improved ELM are sine and cosine functions. In addition, the improved ELM analytically determines the output weights of neural networks. Finally, experimental results are given to verify the efficiency and effectiveness of the improved ELM. (c) 2006 Elsevier B.V. All rights reserved.

引用

页码：2369 / 2373

页数：5

共 11 条

[1]

What Size Net Gives Valid Generalization? [J].