Priyesh Shukla
Papers
2
Total Citations
35
H-Index
2
About
Priyesh Shukla is a researcher at the intersection of neuromorphic computing, edge intelligence, and Bayesian deep learning, with a focus on developing energy-efficient hardware architectures for safety-critical AI applications. His most significant contribution, MC-CIM (2022), introduced a pioneering compute-in-memory framework that integrates Monte Carlo Dropout techniques directly into hardware, enabling deep neural networks to quantify prediction uncertainty without sacrificing power efficiency — a critical advancement for applications where mispredictions carry serious consequences. This work has garnered 32 citations, reflecting strong recognition within the embedded AI and hardware design communities. Building on this foundation, Shukla has extended his uncertainty-aware computing paradigm to the domain of edge robotics, tackling the demanding challenge of pose estimation for insect-scale drones operating in constrained environments. His 2024 work demonstrates a commitment to translating theoretical Bayesian principles into practical, real-world autonomous systems. Across his research portfolio, Shukla consistently bridges the gap between algorithmic robustness and hardware feasibility, making meaningful strides toward trustworthy, low-power AI at the edge — a challenge central to the future of autonomous and embedded intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2