Deepika Sharma

Papers

Total Citations

H-Index

About

Deepika Sharma is an emerging researcher at the forefront of neuromorphic computing and event-based vision, with a focus on developing energy-efficient artificial intelligence systems for robotics and resource-constrained environments. Her work bridges the gap between biological neural computation and practical hardware implementation, positioning her as a notable contributor to next-generation AI architectures. Sharma's most impactful contribution, "Neuromorphic Computing for Robotic Vision: Algorithms to Hardware Advances" (2025, 16 citations), offers a comprehensive systems-level perspective on integrating specialized neuromorphic sensing with efficient computational paradigms, advocating for cohesive design methodologies that span from algorithms to physical hardware. Complementing this, her innovative hybrid SNN-ANN architecture for event-based optical flow estimation demonstrates her ability to synthesize the strengths of both Spiking Neural Networks and conventional Artificial Neural Networks. By leveraging the asynchronous, sparse outputs of event-based cameras, her framework addresses critical challenges in high-speed motion perception and dynamic range processing in robotic vision. With a growing citation record across multiple high-impact publications, Sharma's research is gaining meaningful traction within the neuromorphic and robotics communities, making her work essential reading for students and researchers pursuing the future of low-power, brain-inspired computing systems.