Cascading fuzzy neural networks

Ji cheng Duan; Fu Lai Korris Chung

Cascading fuzzy neural networks

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

A new fuzzy neural network (FNN) model based on syllogistic fuzzy reasoning is proposed in this paper. Unlike most of the proposed FNN models implementing single-stage fuzzy reasoning mechanisms, the new model implements syllogistic fuzzy reasoning which is usually used by human beings. A hybrid learning algorithm is presented to derive an appropriate syllogistic fuzzy rule set and update the corresponding network parameters. It is found that the model is superior to its single-stage counterpart in learning ability and robustness.

Original language	English
Title of host publication	IEEE International Conference on Fuzzy Systems
Publisher	IEEE
Publication status	Published - 1 Dec 1999
Event	Proceedings of the 1999 IEEE International Fuzzy Systems Conference, FUZZ-IEEE'99 - Seoul, Korea, Republic of Duration: 22 Aug 1999 → 25 Aug 1999

Conference

Conference	Proceedings of the 1999 IEEE International Fuzzy Systems Conference, FUZZ-IEEE'99
Country/Territory	Korea, Republic of
City	Seoul
Period	22/08/99 → 25/08/99

ASJC Scopus subject areas

Chemical Health and Safety
Software
Safety, Risk, Reliability and Quality

Cite this

@inproceedings{1d8574c019114144af89a218a74b632a,

title = "Cascading fuzzy neural networks",

abstract = "A new fuzzy neural network (FNN) model based on syllogistic fuzzy reasoning is proposed in this paper. Unlike most of the proposed FNN models implementing single-stage fuzzy reasoning mechanisms, the new model implements syllogistic fuzzy reasoning which is usually used by human beings. A hybrid learning algorithm is presented to derive an appropriate syllogistic fuzzy rule set and update the corresponding network parameters. It is found that the model is superior to its single-stage counterpart in learning ability and robustness.",

author = "Duan, {Ji cheng} and Chung, {Fu Lai Korris}",

year = "1999",

month = dec,

day = "1",

language = "English",

booktitle = "IEEE International Conference on Fuzzy Systems",

publisher = "IEEE",

address = "United States",

note = "Proceedings of the 1999 IEEE International Fuzzy Systems Conference, FUZZ-IEEE'99 ; Conference date: 22-08-1999 Through 25-08-1999",

}

TY - GEN

T1 - Cascading fuzzy neural networks

AU - Duan, Ji cheng

AU - Chung, Fu Lai Korris

PY - 1999/12/1

Y1 - 1999/12/1

N2 - A new fuzzy neural network (FNN) model based on syllogistic fuzzy reasoning is proposed in this paper. Unlike most of the proposed FNN models implementing single-stage fuzzy reasoning mechanisms, the new model implements syllogistic fuzzy reasoning which is usually used by human beings. A hybrid learning algorithm is presented to derive an appropriate syllogistic fuzzy rule set and update the corresponding network parameters. It is found that the model is superior to its single-stage counterpart in learning ability and robustness.

AB - A new fuzzy neural network (FNN) model based on syllogistic fuzzy reasoning is proposed in this paper. Unlike most of the proposed FNN models implementing single-stage fuzzy reasoning mechanisms, the new model implements syllogistic fuzzy reasoning which is usually used by human beings. A hybrid learning algorithm is presented to derive an appropriate syllogistic fuzzy rule set and update the corresponding network parameters. It is found that the model is superior to its single-stage counterpart in learning ability and robustness.

UR - http://www.scopus.com/inward/record.url?scp=0033280535&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

BT - IEEE International Conference on Fuzzy Systems

PB - IEEE

T2 - Proceedings of the 1999 IEEE International Fuzzy Systems Conference, FUZZ-IEEE'99

Y2 - 22 August 1999 through 25 August 1999

ER -

Cascading fuzzy neural networks

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this