Towards Reliable Uncertainty Quantification and High Precision with General Type-2 Fuzzy Systems

Batuhan Avci, Aykut Beke, Tufan Kumbasar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Deep learning models have been successfully developed to solve complex problems with the main focus on high precision. Yet, accurately assessing uncertainty and prediction is essential for making informed decisions, especially in high-risk tasks. In this paper, we present a step towards learning reliable uncertainty quantification and high precision performance via α- plane based General Type-2 Fuzzy Logic Systems (GT2-FLSs). To balance between accuracy and uncertainty quantification, we propose a novel composite loss function consisting of an accuracy-focused and uncertainty-focused loss term that exploits the parameters of the Secondary Membership Functions (SMFs). For the uncertainty-focused term, we use only the type-reduced set of α0= 0 plane of the GT2-FLS, i.e. the size of the SMFs, which does not contribute to the output calculation directly. In the accuracy-focused part, we present two options for the error terms. One uses the aggregated output while the other uses only the output αK= 1 plane of the GT2-FLS. In both terms, we make the SMF shape parameters responsible for learning pointwise prediction. We present statistical comparisons and demonstrate that the learned GT2-FLSs generate reliable prediction intervals while also resulting in high-precision performance. The results show the potential of the proposed approach for GT2-FLS as a promising solution for making reliable predictions in real-world applications.

Original languageEnglish
Title of host publication2023 IEEE International Conference on Fuzzy Systems, FUZZ 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350332285
DOIs
Publication statusPublished - 2023
Event2023 IEEE International Conference on Fuzzy Systems, FUZZ 2023 - Incheon, Korea, Republic of
Duration: 13 Aug 202317 Aug 2023

Publication series

NameIEEE International Conference on Fuzzy Systems
ISSN (Print)1098-7584

Conference

Conference2023 IEEE International Conference on Fuzzy Systems, FUZZ 2023
Country/TerritoryKorea, Republic of
CityIncheon
Period13/08/2317/08/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

* We acknowledge partial funding from TUBITAK grant no. 119E507. ** T. Kumbasar was supported by the TUBA in part by the Outstanding Young Scientist Award Program.

FundersFunder number
TUBA
Türkiye Bilimsel ve Teknolojik Araştırma Kurumu119E507

    Keywords

    • accuracy
    • deep learning
    • general type-2 fuzzy logic systems
    • prediction interval
    • uncertainty

    Fingerprint

    Dive into the research topics of 'Towards Reliable Uncertainty Quantification and High Precision with General Type-2 Fuzzy Systems'. Together they form a unique fingerprint.

    Cite this