Deriving multistage FNN models from Takagi and Sugeno's fuzzy systems

Fu Lai Korris Chung; Ji cheng Duan; Daniel So Yeung

Deriving multistage FNN models from Takagi and Sugeno's fuzzy systems

Fu Lai Korris Chung, Ji cheng Duan, Daniel So Yeung

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

5 Citations (Scopus)

Abstract

Two multistage fuzzy neural network (FNN) models are derived from Takagi and Sugeno's fuzzy systems by arranging single-stage reasoning units (stages) in an incremental and aggregation manner. The dimensionality problem is overcome since the number of rules is reduced to a linear function of the number of inputs. The network structure in each stage is based on Jang's ANFIS model. Through applying LSE and back-propagation algorithms to the training process, the proposed models can learn multistage fuzzy rules from stipulated data pairs. Simulation results show that the proposed multistage FNN models are superior to its single-stage counterpart in resource used (e.g. number of fuzzy rules, number of adjustable parameters etc.), convergence speed and generalization ability.

Original language	English
Title of host publication	IEEE International Conference on Fuzzy Systems
Publisher	IEEE
Pages	1259-1263
Number of pages	5
Publication status	Published - 1 Jan 1998
Event	Proceedings of the 1998 IEEE International Conference on Fuzzy Systems,. Part 2 (of 2) - Anchorage, AK, United States Duration: 4 May 1998 → 9 May 1998

Conference

Conference	Proceedings of the 1998 IEEE International Conference on Fuzzy Systems,. Part 2 (of 2)
Country/Territory	United States
City	Anchorage, AK
Period	4/05/98 → 9/05/98

ASJC Scopus subject areas

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

Cite this

@inproceedings{ed532c24aacd4866ba99a2652b52a69e,

title = "Deriving multistage FNN models from Takagi and Sugeno's fuzzy systems",

abstract = "Two multistage fuzzy neural network (FNN) models are derived from Takagi and Sugeno's fuzzy systems by arranging single-stage reasoning units (stages) in an incremental and aggregation manner. The dimensionality problem is overcome since the number of rules is reduced to a linear function of the number of inputs. The network structure in each stage is based on Jang's ANFIS model. Through applying LSE and back-propagation algorithms to the training process, the proposed models can learn multistage fuzzy rules from stipulated data pairs. Simulation results show that the proposed multistage FNN models are superior to its single-stage counterpart in resource used (e.g. number of fuzzy rules, number of adjustable parameters etc.), convergence speed and generalization ability.",

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

year = "1998",

month = jan,

day = "1",

language = "English",

pages = "1259--1263",

booktitle = "IEEE International Conference on Fuzzy Systems",

publisher = "IEEE",

address = "United States",

note = "Proceedings of the 1998 IEEE International Conference on Fuzzy Systems,. Part 2 (of 2) ; Conference date: 04-05-1998 Through 09-05-1998",

}

TY - GEN

T1 - Deriving multistage FNN models from Takagi and Sugeno's fuzzy systems

AU - Chung, Fu Lai Korris

AU - Duan, Ji cheng

AU - Yeung, Daniel So

PY - 1998/1/1

Y1 - 1998/1/1

N2 - Two multistage fuzzy neural network (FNN) models are derived from Takagi and Sugeno's fuzzy systems by arranging single-stage reasoning units (stages) in an incremental and aggregation manner. The dimensionality problem is overcome since the number of rules is reduced to a linear function of the number of inputs. The network structure in each stage is based on Jang's ANFIS model. Through applying LSE and back-propagation algorithms to the training process, the proposed models can learn multistage fuzzy rules from stipulated data pairs. Simulation results show that the proposed multistage FNN models are superior to its single-stage counterpart in resource used (e.g. number of fuzzy rules, number of adjustable parameters etc.), convergence speed and generalization ability.

AB - Two multistage fuzzy neural network (FNN) models are derived from Takagi and Sugeno's fuzzy systems by arranging single-stage reasoning units (stages) in an incremental and aggregation manner. The dimensionality problem is overcome since the number of rules is reduced to a linear function of the number of inputs. The network structure in each stage is based on Jang's ANFIS model. Through applying LSE and back-propagation algorithms to the training process, the proposed models can learn multistage fuzzy rules from stipulated data pairs. Simulation results show that the proposed multistage FNN models are superior to its single-stage counterpart in resource used (e.g. number of fuzzy rules, number of adjustable parameters etc.), convergence speed and generalization ability.

UR - http://www.scopus.com/inward/record.url?scp=0031627853&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SP - 1259

EP - 1263

BT - IEEE International Conference on Fuzzy Systems

PB - IEEE

T2 - Proceedings of the 1998 IEEE International Conference on Fuzzy Systems,. Part 2 (of 2)

Y2 - 4 May 1998 through 9 May 1998

ER -

Deriving multistage FNN models from Takagi and Sugeno's fuzzy systems

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this