Dongchen Liang

SIB Swiss Institute of Bioinformatics, ETH Zurich

Papers

Total Citations

H-Index

About

Dongchen Liang’s research lies at the intersection of neuromorphic engineering, robust learning, and autonomous control—pioneering how brain-inspired hardware can drive next-generation robotic agents. His major contributions center on developing neural state machines that enable mixed-signal analog/digital neuromorphic circuits to perform reliable, real-time learning and control despite inherent hardware variability. This work directly addresses the critical challenge of making ultra-low-power, low-latency neuromorphic systems practical for real-world robotics. Liang’s most cited paper, “Neural State Machines for Robust Learning and Control of Neuromorphic Agents” (2019), has accumulated 22 citations, reflecting its foundational role in the field. A follow-up study on robust visual pattern recognition in neuromorphic agents (2019) further demonstrates his commitment to overcoming device-level imperfections for stable performance. By bridging theoretical learning algorithms with physical hardware constraints, Liang has helped chart a path toward power-efficient, autonomous systems that can operate in dynamic environments—a key step for applications ranging from edge computing to agile robotics. His work continues to inspire researchers seeking to merge neuroscience principles with practical engineering.