Fangbo Tao

Papers

Total Citations

H-Index

About

Fangbo Tao is a researcher at the forefront of energy-efficient artificial intelligence, with a primary focus on spiking neural networks (SNNs) and neuromorphic computing for real-time, online action recognition. His most cited work, "The spike gating flow: A hierarchical structure-based spiking neural network for online gesture recognition" (2022, 6 citations), addresses a critical bottleneck in deploying deep learning for industrial applications like robotic vision and autonomous vehicles: the prohibitive computational cost of traditional neural networks. Tao’s major contribution lies in designing hierarchical SNN architectures that leverage the inherent efficiency of spike-based computation, enabling online gesture recognition with significantly reduced energy consumption. By introducing the concept of "spike gating flow," his work demonstrates how to maintain high temporal precision while minimizing redundant neural firing—a key step toward practical neuromorphic systems. Though early in his citation impact, this research has already been recognized for its potential to bridge the gap between biological plausibility and industrial deployment. Tao’s work is particularly notable for targeting the intersection of event-driven sensing and real-time control, positioning him as a promising voice in the push toward low-power, brain-inspired AI for edge computing.