Welcome to the InfoSci Platform
Reference Hub2
Input Space Partitioning for Neural Network Learning

Input Space Partitioning for Neural Network Learning

Shujuan Guo, Sheng-Uei Guan, Weifan Li, Ka Lok Man, Fei Liu, A. K. Qin
Copyright: © 2013 |Volume: 4 |Issue: 2 |Pages: 11
ISSN: 1942-3594|EISSN: 1942-3608|EISBN13: 9781466632769|DOI: 10.4018/jaec.2013040105
Cite Article Cite Article

MLA

Guo, Shujuan, et al. "Input Space Partitioning for Neural Network Learning." IJAEC vol.4, no.2 2013: pp.56-66. http://doi.org/10.4018/jaec.2013040105

APA

Guo, S., Guan, S., Li, W., Man, K. L., Liu, F., & Qin, A. K. (2013). Input Space Partitioning for Neural Network Learning. International Journal of Applied Evolutionary Computation (IJAEC), 4(2), 56-66. http://doi.org/10.4018/jaec.2013040105

Chicago

Guo, Shujuan, et al. "Input Space Partitioning for Neural Network Learning," International Journal of Applied Evolutionary Computation (IJAEC) 4, no.2: 56-66. http://doi.org/10.4018/jaec.2013040105

Export Reference

Mendeley
Favorite Full-Issue Download

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.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.