2 papers
cs.LG2026
Reproducible macroscopic dynamics in a closed-loop human-AI learning system
Minlin Wu, Xu Fang, Yicheng Zhang +2
Closed-loop human-AI systems generate high-dimensional behavioural trajectories whose collective dynamics remain obscure. Using 297,915 learners' adaptive-tutoring histories, we de…
physics.data-an2024
Learning from the past: predicting critical transitions with machine learning trained on surrogates of historical data
Zhiqin Ma, Chunhua Zeng, Yi-Cheng Zhang +1
Complex systems can undergo critical transitions, where slowly changing environmental conditions trigger a sudden shift to a new, potentially catastrophic state. Early warning sign…