Shuncheng Jia

University of Chinese Academy of Sciences

Papers

Total Citations

H-Index

About

Shuncheng Jia is a pioneering researcher at the intersection of biologically inspired computing and reinforcement learning, with a primary focus on advancing Spiking Neural Networks (SNNs) for complex control tasks. His major contributions lie in bridging the gap between deep reinforcement learning (DRL) and more brain-like computational models. Jia’s most impactful work, “Multi-Scale Dynamic Coding Improved Spiking Actor Network for Reinforcement Learning” (2022, 32 citations), introduces a novel framework that enhances SNN performance by incorporating multi-scale temporal dynamics, enabling more efficient policy learning in robotic control. His earlier foundational paper, “Population-coding and Dynamic-neurons improved Spiking Actor Network for Reinforcement Learning” (2021, 7 citations), further demonstrates his expertise in leveraging population coding and dynamic neuronal properties to overcome the limitations of traditional artificial neurons. Collectively, Jia’s research addresses a critical challenge in neuromorphic computing: making SNNs competitive with deep neural networks in real-world applications. By integrating biological plausibility with algorithmic efficiency, his work has laid important groundwork for energy-efficient, brain-inspired AI systems. Jia’s contributions are particularly notable for their potential to revolutionize autonomous robotics and edge computing, where low-power, spike-based computation offers significant advantages over conventional DRL approaches.