Input Space Partitioning for Neural Network Learning-Reference-Cited by-同舟云学术

Input Space Partitioning for Neural Network Learning

Published:2013-04 Issue:2 Volume:4 Page:56-66
ISSN:1942-3594
Container-title:International Journal of Applied Evolutionary Computation
language:en
Short-container-title:

Author:

Guo Shujuan¹,Guan Sheng-Uei¹,Li Weifan²,Man Ka Lok²,Liu Fei³,Qin A. K.⁴

Affiliation:

1. School of Electronic & Information Engineering, Xi’an Jiaotong University, Suzhou, Jiangsu, China

2. Dept. of Computer Science and Software Engineering, Xi’an Jiaotong-Liverpool University, Suzhou, China

3. Department of Computer Science & Computer Engineering, La Trobe University, Melbourne, VIC, Australia

4. School of Computer Science and Information Technology, RMIT University, Melbourne, VIC, Australia

Abstract

To improve the learning performance of neural network (NN), this paper introduces an input attribute grouping based NN ensemble method. All of the input attributes are partitioned into exclusive groups according to the degree of inter-attribute promotion or correlation that quantifies the supportive interactions between attributes. After partitioning, multiple NNs are trained by taking each group of attributes as their respective inputs. The final classification result is obtained by integrating the results from each NN. Experimental results on several UCI datasets demonstrate the effectiveness of the proposed method.

Publisher

IGI Global

Subject

General Earth and Planetary Sciences,General Environmental Science

Reference18 articles.

1. Dynamic Node Creation in Backpropagation Networks

2. Bahler, D., & Navarro, L. (2000). Methods for combining heterogeneous sets of classifiers. In Proceedings of the 17th National Conference on Artificial Intelligence (AAAI), Workshop on New Research Problems for Machine Learning.

3. Bagging predictors

4. Dietterich, T. (2000). Ensemble methods in machine learning. Multiple classifier systems, 1-15.

5. Fahlman, S. E., & Lebiere, C. (1989). The cascade-correlation learning architecture.

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. An Output Grouping Based Approach to Multiclass Classification Using Support Vector Machines;Lecture Notes in Electrical Engineering;2016

2. Neural Incremental Attribute Learning in Groups;International Journal of Computational Intelligence Systems;2015