A MODIFIED LEARNING ALGORITHM INCORPORATING ADDITIONAL FUNCTIONAL CONSTRAINTS INTO NEURAL NETWORKS

Author:

HAN FEI12,LI XU-QIN1,LYU MICHAEL R.3,LOK TAT-MING4

Affiliation:

1. Hefei Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, Anhui 230031, P. R. China

2. Department of Automation, University of Science and Technology of China, Hefei, Anhui 230027, P. R. China

3. Computer Science and Engineering Department, The Chinese University of Hong Kong, Shatin, Hong Kong, China

4. Information Engineering Department, The Chinese University of Hong Kong, Shatin, Hong Kong, China

Abstract

In this paper, a modified learning algorithm to obtain better generalization performance is proposed. The cost terms of this new algorithm are selected based on the second-order derivatives of the neural activation at the hidden layers and the first-order derivatives of the neural activation at the output layer. It can be guaranteed that in the course of training, the additional cost terms for this algorithm can penalize both the input-to-output mapping sensitivity and the high frequency components to obtain better generalization performance. Finally, theoretical justifications and simulation results are given to verify the efficiency and effectiveness of the proposed learning algorithm.

Publisher

World Scientific Pub Co Pte Lt

Subject

Artificial Intelligence,Computer Vision and Pattern Recognition,Software

Reference15 articles.

1. Neural modeling for time series: A statistical stepwise method for weight elimination

2. Regularization with a Pruning Prior

3. D. S. Huang, Systematic Theory of Neural Networks for Pattern Recognition (Publishing House of Electronic Industry of China, Beijing, 1996) pp. 111–118.

4. Lecture Notes in Computer Science;Huang D. S.,2003

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. A parametric study of machine learning techniques in petroleum reservoir permeability prediction by integrating seismic attributes and wireline data;Journal of Petroleum Science and Engineering;2019-05

2. FUZZY COGNITIVE MAPS FOR PATTERN RECOGNITION APPLICATIONS;International Journal of Pattern Recognition and Artificial Intelligence;2008-12

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3