Multiple Network Fusion Using Fuzzy Logic

Research output: Contribution to journalArticlepeer-review

164 Citations (Scopus)


Multiplayer feedforward networks trained by minimizing the mean squared error and by using a one of c teaching function yield network outputs that estimate posterior class probabilities. This provides a sound basis for combining the results from multiple networks to get more accurate classification. This paper presents a method for combining multiple networks based on fuzzy logic, especially the fuzzy integral. This method non-linearly combines objective evidence, in the form of a network output, with subjective evaluation of the importance of the individual neural networks. The experimental results with the recognition problem of on-line handwriting characters show that the performance of individual networks could be improved significantly.

Original languageEnglish
Pages (from-to)497-501
Number of pages5
JournalIEEE Transactions on Neural Networks
Issue number2
Publication statusPublished - 1995 Mar

Bibliographical note

Funding Information:
An altemative is to independently generate a number of networks for possible generalizers and utilized all of them for obtaining robust output. While a usual scheme chooses one best network from amongst the set of candidate networks based on a winner-takes-all strategy, this approach keeps multiple networks and runs them all with an appropriate collective decision strategy. This is different from the aforementioned "adaptive mixtures of local experts" [3], in the sense that here networks do not decompose the task, but learn globally the same task with different points of view. A general result from the previous works is that averaging separate networks improves generalization performance for the mean :quared error [5]. If we have Manuscript received June 4, 1993; revised August 13, 1994. This work was supported in part by a grant from the Korea Science and Engineering Foundation (KOSEF). S. B. Cho is with ATR Human Information Processing Research Laboratories, Kyoto 619-02, Japan. J. H. Kim is with KAIST Center for Artificial Intelligence Research, Taejeon, 305-701, Republic of Korea. IEEE Log Number 9408102.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence


Dive into the research topics of 'Multiple Network Fusion Using Fuzzy Logic'. Together they form a unique fingerprint.

Cite this