Shubham Negi
Papers
2
Total Citations
8
H-Index
2
About
Shubham Negi is an emerging researcher working at the intersection of neuromorphic computing, computer vision, and robotics. His most notable work centers on developing innovative neural network architectures that bridge the gap between biological and artificial intelligence, with a particular focus on event-based perception systems. His most cited contribution, "Best of Both Worlds: Hybrid SNN-ANN Architecture for Event-based Optical Flow Estimation," demonstrates his ability to synthesize the complementary strengths of Spiking Neural Networks (SNNs) and Artificial Neural Networks (ANNs) into a unified framework tailored for event-based cameras. This research addresses a critical challenge in robotics: efficiently processing high-speed motion and high dynamic range scenes using low-power, asynchronous sensory data. By combining the temporal sparsity and energy efficiency of SNNs with the representational power of conventional ANNs, Negi's hybrid approach offers a compelling solution for real-time optical flow estimation. With 4 citations already accrued, his work is gaining traction within the neuromorphic and robotics communities. For students and researchers exploring energy-efficient AI and next-generation robotic perception, Negi's contributions represent a promising and timely direction in the field.
Research Focus
Key Achievements
Top Papers
- 1
- 2