Somnath Paul
Papers
1
Total Citations
33
H-Index
1
About
Somnath Paul is a leading researcher in neuromorphic computing and brain-inspired hardware design, with a focus on enabling embedded, continual learning for autonomous systems. His most-cited work, the "Neural and Synaptic Array Transceiver" (2018, 33 citations), introduces a groundbreaking algorithmic framework that overcomes key limitations in large-scale neuromorphic implementations—namely, the trade-off between flexibility and efficiency. By developing a transceiver architecture that integrates neural and synaptic processing, Paul has paved the way for adaptive, real-time learning in resource-constrained environments, such as robotics and edge devices. His contributions address critical challenges in deploying artificial intelligence that can learn autonomously without external supervision, a feat that has garnered attention for its potential to revolutionize embedded AI. Beyond this flagship paper, Paul’s research spans synaptic array design, energy-efficient computing, and hardware-software co-optimization, consistently pushing the boundaries of what is possible in low-power, brain-inspired systems. His work is highly regarded for its practical impact, offering a scalable path toward machines that learn and adapt in the field.
Research Focus
Key Achievements
Top Papers
- 1