Volume 12 Issue 3
Apr.  2017
Article Contents

Rong-Fang Xu, Thao-Tsen Chen, Shie-Jue Lee. Weighted Learning for Feedforward Neural Networks[J]. Journal of Electronic Science and Technology, 2014, 12(3): 299-304. doi: 10.3969/j.issn.1674-862X.2014.03.011
Citation: Rong-Fang Xu, Thao-Tsen Chen, Shie-Jue Lee. Weighted Learning for Feedforward Neural Networks[J]. Journal of Electronic Science and Technology, 2014, 12(3): 299-304. doi: 10.3969/j.issn.1674-862X.2014.03.011

Weighted Learning for Feedforward Neural Networks

doi: 10.3969/j.issn.1674-862X.2014.03.011
Funds:

This work was supported by the NSC under Grant No. NSC-100-2221-E- 110-083-MY3 and NSC-101-2622-E-110-011-CC3, and also by "Aim for the Top University Plan" of the National Sun-Yat-Sen University and Ministry of Education.

More Information
  • Author Bio:

    Rong-Fang Xu research interests include data mining and machine learning, rfxu@water.ee.nsysu.edu.tw;
    Shie-Jue Lee research interests include artificial intelligence, machine learning, data mining, information retrieval, and soft computing, leesj@mail.ee.nsysu.edu.tw;
    Thao-Tsen Chen, ttchen@water.ee.nsysu.edu.tw

    Rong-Fang Xu research interests include data mining and machine learning, rfxu@water.ee.nsysu.edu.tw;
    Shie-Jue Lee research interests include artificial intelligence, machine learning, data mining, information retrieval, and soft computing, leesj@mail.ee.nsysu.edu.tw;
    Thao-Tsen Chen, ttchen@water.ee.nsysu.edu.tw

    Rong-Fang Xu research interests include data mining and machine learning, rfxu@water.ee.nsysu.edu.tw;
    Shie-Jue Lee research interests include artificial intelligence, machine learning, data mining, information retrieval, and soft computing, leesj@mail.ee.nsysu.edu.tw;
    Thao-Tsen Chen, ttchen@water.ee.nsysu.edu.tw

  • Authors’ information: Shie-Jue Lee
  • Received Date: 2013-12-07
  • Rev Recd Date: 2014-03-10
  • Publish Date: 2014-09-25

通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Article Metrics

Article views(220) PDF downloads(28) Cited by()

Related
Proportional views

Weighted Learning for Feedforward Neural Networks

doi: 10.3969/j.issn.1674-862X.2014.03.011
Funds:

This work was supported by the NSC under Grant No. NSC-100-2221-E- 110-083-MY3 and NSC-101-2622-E-110-011-CC3, and also by "Aim for the Top University Plan" of the National Sun-Yat-Sen University and Ministry of Education.

  • Author Bio:

  • Corresponding author: Shie-Jue Lee

Abstract: In this paper, we propose two weighted learning methods for the construction of single hidden layer feedforward neural networks. Both methods incorporate weighted least squares. Our idea is to allow the training instances nearer to the query to offer bigger contributions to the estimated output. By minimizing the weighted mean square error function, optimal networks can be obtained. The results of a number of experiments demonstrate the effectiveness of our proposed methods.

Rong-Fang Xu, Thao-Tsen Chen, Shie-Jue Lee. Weighted Learning for Feedforward Neural Networks[J]. Journal of Electronic Science and Technology, 2014, 12(3): 299-304. doi: 10.3969/j.issn.1674-862X.2014.03.011
Citation: Rong-Fang Xu, Thao-Tsen Chen, Shie-Jue Lee. Weighted Learning for Feedforward Neural Networks[J]. Journal of Electronic Science and Technology, 2014, 12(3): 299-304. doi: 10.3969/j.issn.1674-862X.2014.03.011

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return