Sharat Chidambaran

University at Buffalo, State University of New York

Papers

Total Citations

H-Index

About

Sharat Chidambaran is a researcher focused on advancing autonomous systems through the intersection of artificial neural networks (ANNs) and evolutionary computation. His primary research areas include neuro-evolution, multi-criteria optimization, and adaptive topology design for intelligent agents. Chidambaran’s major contribution lies in challenging the conventional use of fixed, user-prescribed network topologies in autonomous systems, which often result in sub-optimal performance and limited portability. By extending the neuro-evolution of augmenting topologies (NEAT) paradigm, he has pioneered methods that dynamically evolve network structures based on both experiential learning and performance metrics. His most cited work, “Multi-Criteria Evolution of Neural Network Topologies” (2018), has garnered 4 citations and serves as a foundational piece for researchers seeking more flexible, self-optimizing control systems. This work highlights his commitment to creating robust, adaptable architectures that can balance competing demands in real-world environments. Chidambaran’s research is particularly relevant for students and engineers developing next-generation robotics and autonomous vehicles, offering a path toward systems that can autonomously refine their own cognitive frameworks.