Samuel Dekhterman
University of Illinois Urbana-Champaign, United States Army Corps of Engineers
Papers
2
Total Citations
7
H-Index
1
About
Samuel Dekhterman is a rising researcher at the forefront of computational intelligence, specializing in the design and optimization of advanced fuzzy inference systems. His primary research areas include adaptive neuro-fuzzy systems, hierarchical rule-base reduction, and reinforcement learning-based optimization. Dekhterman’s major contribution lies in pioneering a novel approach that integrates Hierarchical Rule-Base Reduction (HRBR) with Adaptive-Network-Based Fuzzy Inference Systems (ANFIS), significantly enhancing computational efficiency for symmetric linguistic variables. By coupling this architecture with an online optimization framework powered by Deep Deterministic Policy Gradient (DDPG), he has introduced a dynamic method for real-time system tuning that overcomes the limitations of traditional static models. His most cited work, published in 2024, has already garnered 6 citations, signaling strong early impact in the field. This innovative fusion of fuzzy logic and deep reinforcement learning offers a scalable solution for complex control and decision-making tasks. Dekhterman’s work is particularly notable for its practical implications in autonomous systems and adaptive control, positioning him as a promising young scholar bridging the gap between symbolic reasoning and modern machine learning.
Research Focus
Key Achievements
Top Papers
- 1
- 2