Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Zadeh's Type-2 Fuzzy Logic Systems: Precision and High-Quality Prediction Intervals (2404.12800v1)

Published 19 Apr 2024 in cs.LG and cs.AI

Abstract: General Type-2 (GT2) Fuzzy Logic Systems (FLSs) are perfect candidates to quantify uncertainty, which is crucial for informed decisions in high-risk tasks, as they are powerful tools in representing uncertainty. In this paper, we travel back in time to provide a new look at GT2-FLSs by adopting Zadeh's (Z) GT2 Fuzzy Set (FS) definition, intending to learn GT2-FLSs that are capable of achieving reliable High-Quality Prediction Intervals (HQ-PI) alongside precision. By integrating Z-GT2-FS with the (\alpha)-plane representation, we show that the design flexibility of GT2-FLS is increased as it takes away the dependency of the secondary membership function from the primary membership function. After detailing the construction of Z-GT2-FLSs, we provide solutions to challenges while learning from high-dimensional data: the curse of dimensionality, and integrating Deep Learning (DL) optimizers. We develop a DL framework for learning dual-focused Z-GT2-FLSs with high performances. Our study includes statistical analyses, highlighting that the Z-GT2-FLS not only exhibits high-precision performance but also produces HQ-PIs in comparison to its GT2 and IT2 fuzzy counterparts which have more learnable parameters. The results show that the Z-GT2-FLS has a huge potential in uncertainty quantification.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (22)
  1. M. Abdar et al., “A review of uncertainty quantification in deep learning: Techniques, applications and challenges,” Inf. Fusion., vol. 76, pp. 243–297, 2021.
  2. H. Papadopoulos, V. Vovk, and A. Gammerman, “Regression conformal prediction with nearest neighbours,” J. Artif. Intell., vol. 40, pp. 815–840, 2011.
  3. T. Pearce, A. Brintrup, M. Zaki, and A. Neely, “High-quality prediction intervals for deep learning: A distribution-free, ensembled approach,” in Int. Conf. Mach. Learn., vol. 80, 2018.
  4. H. Quan, D. Srinivasan, and A. Khosravi, “Short-term load and wind power forecasting using neural network-based prediction intervals,” IEEE Trans. Neur. Net. Learn. Syst., vol. 25, no. 2, pp. 303–315, 2014.
  5. A. Sakalli, T. Kumbasar, and J. M. Mendel, “Towards systematic design of general type-2 fuzzy logic controllers: Analysis, interpretation, and tuning,” IEEE Trans. Fuzzy Syst., vol. 29, no. 2, pp. 226–239, 2021.
  6. M. Almaraash, M. Abdulrahim, and H. Hagras, “A life-long learning xai metaheuristic-based type-2 fuzzy system for solar radiation modelling,” IEEE Trans. Fuzzy Syst., 2023.
  7. D. Pekaslan, C. Wagner, and J. M. Garibaldi, “Leveraging it2 input fuzzy sets in non-singleton fuzzy logic systems to dynamically adapt to varying uncertainty levels,” in IEEE Int. Conf. Fuzzy Syst., 2019.
  8. J. M. Mendel, “Comparing the performance potentials of interval and general type-2 rule-based fuzzy systems in terms of sculpting the state space,” IEEE Trans. Fuzzy Syst., vol. 27, no. 1, pp. 58–71, 2018.
  9. L.A. Zadeh, “The concept of a linguistic variable and its application to approximate reasoning—i,” Inf. Sci., vol. 8, no. 3, pp. 199–249, 1975.
  10. ——, “Quantitative fuzzy semantics,” Inf. Sci., vol. 3, no. 2, pp. 159–176, 1971.
  11. J. Mendel and R. John, “Type-2 fuzzy sets made simple,” IEEE Trans. Fuzzy Syst., vol. 10, no. 2, pp. 117–127, 2002.
  12. C. Wagner and H. Hagras, “Toward general type-2 fuzzy logic systems based on zslices,” IEEE Trans. Fuzzy Syst., vol. 18, no. 4, pp. 637–660, 2010.
  13. K. Shihabudheen and G. N. Pillai, “Recent advances in neuro-fuzzy system: A survey,” Knowl Based Syst., vol. 152, pp. 136–162, 2018.
  14. Y. Zheng, Z. Xu, and X. Wang, “The fusion of deep learning and fuzzy systems: A state-of-the-art survey,” IEEE Trans. Fuzzy Syst., vol. 30, no. 8, pp. 2783–2799, 2021.
  15. K. Wiktorowicz, “T2rfis: type-2 regression-based fuzzy inference system,” Neural Comput. Appl., vol. 35, no. 27, pp. 20 299–20 317, 2023.
  16. J. Tavoosi, A. Mohammadzadeh, and K. Jermsittiparsert, “A review on type-2 fuzzy neural networks for system identification,” Soft Computing, vol. 25, pp. 7197–7212, 2021.
  17. H. Han, Z. Liu, H. Liu, J. Qiao, and C. P. Chen, “Type-2 fuzzy broad learning system,” IEEE Trans. Cybern., vol. 52, no. 10, pp. 10 352–10 363, 2021.
  18. A. Beke and T. Kumbasar, “More than accuracy: A composite learning framework for interval type-2 fuzzy logic systems,” IEEE Trans. Fuzzy Syst., vol. 31, no. 3, pp. 734–744, 2023.
  19. B. Avcı, A. Beke, and T. Kumbasar, “Towards reliable uncertainty quantification and high precision with general type-2 fuzzy systems,” in IEEE Int. Conf. Fuzzy Syst., 2023.
  20. H. Bustince et al., “A historical account of types of fuzzy sets and their relationships,” IEEE Trans. Fuzzy Syst., vol. 24, no. 1, pp. 179–194, 2016.
  21. Y. Cui, D. Wu, and Y. Xu, “Curse of dimensionality for tsk fuzzy neural networks: Explanation and solutions,” in Proc. Int. Jt. Conf. Neural Netw., 2021.
  22. A. Köklü, Y. Güven, and T. Kumbasar, “Enhancing interval type-2 fuzzy logic systems: Learning for precision and prediction intervals,” in IEEE Int. Conf. Fuzzy Syst., 2024.
Citations (1)

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets