Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning

Ata Köklü; Yusuf Güven; Tufan Kumbasar

doi:10.1007/978-3-031-70018-7_46

Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning

Ata Köklü, Yusuf Güven, Tufan Kumbasar^*

^*Corresponding author for this work

Department of Control and Automation Engineering

Istanbul Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Type-1 and Interval Type-2 (IT2) Fuzzy Logic Systems (FLS) excel in handling uncertainty alongside their parsimonious rule-based structure. Yet, in learning large-scale data challenges arise, such as the curse of dimensionality and training complexity of FLSs. The complexity is due mainly to the constraints to be satisfied as the learnable parameters define FSs and the complexity of the center of the sets calculation method, especially of IT2-FLSs. This paper explicitly focuses on the learning problem of FLSs and presents a computationally efficient learning method embedded within the realm of Deep Learning (DL). The proposed method tackles the learning challenges of FLSs by presenting computationally efficient implementations of FLSs, thereby minimizing training time while leveraging mini-batched DL optimizers and automatic differentiation provided within the DL frameworks. We illustrate the efficiency of the DL framework for FLSs on benchmark datasets.

Original language	English
Title of host publication	Intelligent and Fuzzy Systems - Intelligent Industrial Informatics and Efficient Networks Proceedings of the INFUS 2024 Conference
Editors	Cengiz Kahraman, Sezi Cevik Onar, Selcuk Cebi, Basar Oztaysi, Irem Ucal Sari, A. Cagrı Tolga
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	406-413
Number of pages	8
ISBN (Print)	9783031700170
DOIs	https://doi.org/10.1007/978-3-031-70018-7_46
Publication status	Published - 2024
Event	International Conference on Intelligent and Fuzzy Systems, INFUS 2024 - Canakkale, Turkey Duration: 16 Jul 2024 → 18 Jul 2024

Publication series

Name	Lecture Notes in Networks and Systems
Volume	1088 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	International Conference on Intelligent and Fuzzy Systems, INFUS 2024
Country/Territory	Turkey
City	Canakkale
Period	16/07/24 → 18/07/24

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Keywords

big data
deep learning
Fuzzy logic systems
learning

Access to Document

10.1007/978-3-031-70018-7_46

Cite this

Köklü, A., Güven, Y., & Kumbasar, T. (2024). Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning. In C. Kahraman, S. Cevik Onar, S. Cebi, B. Oztaysi, I. Ucal Sari, & A. C. Tolga (Eds.), Intelligent and Fuzzy Systems - Intelligent Industrial Informatics and Efficient Networks Proceedings of the INFUS 2024 Conference (pp. 406-413). (Lecture Notes in Networks and Systems; Vol. 1088 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-70018-7_46

Köklü, Ata ; Güven, Yusuf ; Kumbasar, Tufan. / Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning. Intelligent and Fuzzy Systems - Intelligent Industrial Informatics and Efficient Networks Proceedings of the INFUS 2024 Conference. editor / Cengiz Kahraman ; Sezi Cevik Onar ; Selcuk Cebi ; Basar Oztaysi ; Irem Ucal Sari ; A. Cagrı Tolga. Springer Science and Business Media Deutschland GmbH, 2024. pp. 406-413 (Lecture Notes in Networks and Systems).

@inproceedings{e6416968b9cf40d085b7e114e0adfcb8,

title = "Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning",

abstract = "Type-1 and Interval Type-2 (IT2) Fuzzy Logic Systems (FLS) excel in handling uncertainty alongside their parsimonious rule-based structure. Yet, in learning large-scale data challenges arise, such as the curse of dimensionality and training complexity of FLSs. The complexity is due mainly to the constraints to be satisfied as the learnable parameters define FSs and the complexity of the center of the sets calculation method, especially of IT2-FLSs. This paper explicitly focuses on the learning problem of FLSs and presents a computationally efficient learning method embedded within the realm of Deep Learning (DL). The proposed method tackles the learning challenges of FLSs by presenting computationally efficient implementations of FLSs, thereby minimizing training time while leveraging mini-batched DL optimizers and automatic differentiation provided within the DL frameworks. We illustrate the efficiency of the DL framework for FLSs on benchmark datasets.",

keywords = "big data, deep learning, Fuzzy logic systems, learning",

author = "Ata K{\"o}kl{\"u} and Yusuf G{\"u}ven and Tufan Kumbasar",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.; International Conference on Intelligent and Fuzzy Systems, INFUS 2024 ; Conference date: 16-07-2024 Through 18-07-2024",

year = "2024",

doi = "10.1007/978-3-031-70018-7_46",

language = "English",

isbn = "9783031700170",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "406--413",

editor = "Cengiz Kahraman and {Cevik Onar}, Sezi and Selcuk Cebi and Basar Oztaysi and {Ucal Sari}, Irem and Tolga, {A. Cagrı}",

booktitle = "Intelligent and Fuzzy Systems - Intelligent Industrial Informatics and Efficient Networks Proceedings of the INFUS 2024 Conference",

address = "Germany",

}

Köklü, A, Güven, Y & Kumbasar, T 2024, Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning. in C Kahraman, S Cevik Onar, S Cebi, B Oztaysi, I Ucal Sari & AC Tolga (eds), Intelligent and Fuzzy Systems - Intelligent Industrial Informatics and Efficient Networks Proceedings of the INFUS 2024 Conference. Lecture Notes in Networks and Systems, vol. 1088 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 406-413, International Conference on Intelligent and Fuzzy Systems, INFUS 2024, Canakkale, Turkey, 16/07/24. https://doi.org/10.1007/978-3-031-70018-7_46

Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning. / Köklü, Ata; Güven, Yusuf; Kumbasar, Tufan.
Intelligent and Fuzzy Systems - Intelligent Industrial Informatics and Efficient Networks Proceedings of the INFUS 2024 Conference. ed. / Cengiz Kahraman; Sezi Cevik Onar; Selcuk Cebi; Basar Oztaysi; Irem Ucal Sari; A. Cagrı Tolga. Springer Science and Business Media Deutschland GmbH, 2024. p. 406-413 (Lecture Notes in Networks and Systems; Vol. 1088 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning

AU - Köklü, Ata

AU - Güven, Yusuf

AU - Kumbasar, Tufan

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

PY - 2024

Y1 - 2024

N2 - Type-1 and Interval Type-2 (IT2) Fuzzy Logic Systems (FLS) excel in handling uncertainty alongside their parsimonious rule-based structure. Yet, in learning large-scale data challenges arise, such as the curse of dimensionality and training complexity of FLSs. The complexity is due mainly to the constraints to be satisfied as the learnable parameters define FSs and the complexity of the center of the sets calculation method, especially of IT2-FLSs. This paper explicitly focuses on the learning problem of FLSs and presents a computationally efficient learning method embedded within the realm of Deep Learning (DL). The proposed method tackles the learning challenges of FLSs by presenting computationally efficient implementations of FLSs, thereby minimizing training time while leveraging mini-batched DL optimizers and automatic differentiation provided within the DL frameworks. We illustrate the efficiency of the DL framework for FLSs on benchmark datasets.

AB - Type-1 and Interval Type-2 (IT2) Fuzzy Logic Systems (FLS) excel in handling uncertainty alongside their parsimonious rule-based structure. Yet, in learning large-scale data challenges arise, such as the curse of dimensionality and training complexity of FLSs. The complexity is due mainly to the constraints to be satisfied as the learnable parameters define FSs and the complexity of the center of the sets calculation method, especially of IT2-FLSs. This paper explicitly focuses on the learning problem of FLSs and presents a computationally efficient learning method embedded within the realm of Deep Learning (DL). The proposed method tackles the learning challenges of FLSs by presenting computationally efficient implementations of FLSs, thereby minimizing training time while leveraging mini-batched DL optimizers and automatic differentiation provided within the DL frameworks. We illustrate the efficiency of the DL framework for FLSs on benchmark datasets.

KW - big data

KW - deep learning

KW - Fuzzy logic systems

KW - learning

UR - http://www.scopus.com/inward/record.url?scp=85203592816&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-70018-7_46

DO - 10.1007/978-3-031-70018-7_46

M3 - Conference contribution

AN - SCOPUS:85203592816

SN - 9783031700170

T3 - Lecture Notes in Networks and Systems

SP - 406

EP - 413

BT - Intelligent and Fuzzy Systems - Intelligent Industrial Informatics and Efficient Networks Proceedings of the INFUS 2024 Conference

A2 - Kahraman, Cengiz

A2 - Cevik Onar, Sezi

A2 - Cebi, Selcuk

A2 - Oztaysi, Basar

A2 - Ucal Sari, Irem

A2 - Tolga, A. Cagrı

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Conference on Intelligent and Fuzzy Systems, INFUS 2024

Y2 - 16 July 2024 through 18 July 2024

ER -

Köklü A, Güven Y, Kumbasar T. Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning. In Kahraman C, Cevik Onar S, Cebi S, Oztaysi B, Ucal Sari I, Tolga AC, editors, Intelligent and Fuzzy Systems - Intelligent Industrial Informatics and Efficient Networks Proceedings of the INFUS 2024 Conference. Springer Science and Business Media Deutschland GmbH. 2024. p. 406-413. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-031-70018-7_46