Multiple Network Fusion Using Fuzzy Logic

Sung Bae Cho

doi:10.1109/72.363487

Multiple Network Fusion Using Fuzzy Logic

Sung Bae Cho

College of Computing

Research output: Contribution to journal › Article › peer-review

164 Citations (Scopus)

Abstract

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 language	English
Pages (from-to)	497-501
Number of pages	5
Journal	IEEE Transactions on Neural Networks
Volume	6
Issue number	2
DOIs	https://doi.org/10.1109/72.363487
Publication status	Published - 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

Access to Document

10.1109/72.363487

Cite this

@article{4cb8230f24384ca3a2bb852b6b79cd4a,

title = "Multiple Network Fusion Using Fuzzy Logic",

abstract = "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.",

author = "Cho, {Sung Bae}",

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.",

year = "1995",

month = mar,

doi = "10.1109/72.363487",

language = "English",

volume = "6",

pages = "497--501",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

publisher = "IEEE Computational Intelligence Society",

number = "2",

}

TY - JOUR

T1 - Multiple Network Fusion Using Fuzzy Logic

AU - Cho, Sung Bae

N1 - 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.

PY - 1995/3

Y1 - 1995/3

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0029264250&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029264250&partnerID=8YFLogxK

U2 - 10.1109/72.363487

DO - 10.1109/72.363487

M3 - Article

AN - SCOPUS:0029264250

SN - 1045-9227

VL - 6

SP - 497

EP - 501

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

IS - 2

ER -

Multiple Network Fusion Using Fuzzy Logic

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this