Fuzzy Logic
Fuzzy logic, a superset of Boolean logic allowing for continuous truth values between 0 and 1, aims to model and manage uncertainty in complex systems. Current research focuses on integrating fuzzy logic with other techniques, such as deep learning (e.g., Logic Tensor Networks) and model predictive control, to improve the performance and interpretability of various applications. This approach finds utility in diverse fields, from robotics and control systems (e.g., mobile robot navigation, assistive exoskeletons) to medical diagnosis, climate risk assessment, and even enhancing the explainability of complex machine learning models. The ability to handle imprecise information and model nuanced relationships makes fuzzy logic a valuable tool for addressing real-world problems where traditional binary logic falls short.
Papers
Enhancing Interval Type-2 Fuzzy Logic Systems: Learning for Precision and Prediction Intervals
Ata Koklu, Yusuf Guven, Tufan Kumbasar
Zadeh's Type-2 Fuzzy Logic Systems: Precision and High-Quality Prediction Intervals
Yusuf Guven, Ata Koklu, Tufan Kumbasar
Efficient Learning of Fuzzy Logic Systems for Large-Scale Data Using Deep Learning
Ata Koklu, Yusuf Guven, Tufan Kumbasar