Yang‐Yu Liu

Papers

Total Citations

H-Index

About

Yang-Yu Liu is a computational researcher whose work bridges machine learning architecture and the dynamics of collective behavior in biological and artificial systems. Liu's most influential contributions center on the optimization of Echo State Networks (ESNs), a powerful class of recurrent neural networks with broad applications spanning robotics, medicine, finance, and natural language processing. His landmark 2020 paper, "Tailoring Echo State Networks for Optimal Learning," has garnered 29 citations and advances understanding of how reservoir topology — the directed, weighted network of neurons at the heart of ESNs — can be strategically engineered to maximize learning performance. This work builds on earlier theoretical foundations established in his 2017 study on tailoring artificial neural networks more broadly. Beyond neural network design, Liu has made notable strides in swarm intelligence, with his 2024 paper on motion salience and collective behavior earning 17 citations. That work proposes a novel heuristic framework to quantify perception in animal groups, with meaningful implications for swarm robotics. Together, these contributions position Liu as a versatile researcher shaping both the theoretical underpinnings and practical applications of intelligent, adaptive systems.