Dighanchal Banerjee

Papers

Total Citations

H-Index

About

Dighanchal Banerjee is a researcher at the forefront of neuromorphic computing, specializing in spiking neural networks (SNNs) and event-based vision. His work focuses on designing biologically inspired architectures that process sensory data with exceptional efficiency, bridging the gap between neuroscience and practical machine learning. Banerjee’s most cited paper, "A Reservoir-based Convolutional Spiking Neural Network for Gesture Recognition from DVS Input" (2020, 35 citations), introduces a novel hybrid model that combines reservoir computing with convolutional SNNs to recognize dynamic gestures from dynamic vision sensor (DVS) data. This contribution demonstrates how SNNs can effectively capture spatio-temporal patterns while maintaining low power consumption—a critical advantage for edge computing and robotics. By leveraging the precise timing of neural spikes, Banerjee’s approach achieves robust performance on neuromorphic hardware, advancing the field toward real-time, energy-efficient AI systems. His work has been influential in the growing community exploring SNNs for sensory processing, earning recognition for its innovative fusion of computational neuroscience and engineering. Banerjee continues to push boundaries in event-driven learning, making him a key figure in the next generation of intelligent, brain-inspired computing.