Clarkson University Develops KANDy for Discovering Equations in Complex Systems

Researchers at Clarkson University have developed an AI tool called KANDy (Kolmogorov-Arnold Networks for Dynamics) that can uncover the mathematical equations governing complex and chaotic systems directly from data. KANDy, based on Kolmogorov-Arnold Networks, is designed for systems that are noisy, nonlinear, or highly unpredictable, providing both predictive power and interpretability. This tool successfully recovered topological structures in mathematical objects like the Hopf fibration, demonstrating its ability to capture deeper properties of complex systems.