Abstract
This paper presents an efficient fuzzy neural system which consists of modular neural networks combined by the fuzzy integral with ordered weighted averaging (OWA) operators. The ability of the fuzzy integral to combine the results of multiple sources of information has been established in several previous works. The key point of this paper is to formalize modular neural networks as information sources, and show the feasibility of the fuzzy integral extended by OWA operators in the problem of combining neural outputs, especially in the case that the networks differ substantially from each other in accuracy. The experimental results with the recognition problem for on-line handwritten characters show that the performance of individual networks is improved significantly.
| Original language | English |
|---|---|
| Pages (from-to) | 359-375 |
| Number of pages | 17 |
| Journal | International Journal of Approximate Reasoning |
| Volume | 13 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - 1995 Nov |
Bibliographical note
Funding Information:The author would like to thank the three anonymous referees for their constructive criticisms and helpful comments on the earlier version of this manuscript. This work was supported in part from Center for Artificial Intelligence Research (CAIR), the Engineering Research Center (ERC) of Excellence Program in Korea.
All Science Journal Classification (ASJC) codes
- Software
- Theoretical Computer Science
- Artificial Intelligence
- Applied Mathematics