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 language | English |
---|---|
Title of host publication | 2023 IEEE International Conference on Fuzzy Systems, FUZZ 2023 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9798350332285 |
DOIs | |
Publication status | Published - 2023 |
Event | 2023 IEEE International Conference on Fuzzy Systems, FUZZ 2023 - Incheon, Korea, Republic of Duration: 13 Aug 2023 → 17 Aug 2023 |
Publication series
Name | IEEE International Conference on Fuzzy Systems |
---|---|
ISSN (Print) | 1098-7584 |
Conference
Conference | 2023 IEEE International Conference on Fuzzy Systems, FUZZ 2023 |
---|---|
Country/Territory | Korea, Republic of |
City | Incheon |
Period | 13/08/23 → 17/08/23 |
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.
Funders | Funder number |
---|---|
TUBA | |
Türkiye Bilimsel ve Teknolojik Araştırma Kurumu | 119E507 |
Keywords
- accuracy
- deep learning
- general type-2 fuzzy logic systems
- prediction interval
- uncertainty