Machine Learning at the Flatiron Institute Seminar: Ziming Liu
Title: Towards Unification of Artificial Intelligence and Science
Abstract: A major challenge of AI + Science lies in their inherent incompatibility: today’s AI is primarily based on connectionism, while science depends on symbolism. In the first part of the talk, I will talk about Kolmogorov-Arnold Networks (KANs) as a solution to synergize both worlds. Inspired by Kolmogorov-Arnold representation theorem, KANs are more aligned with symbolic representations than MLPs, and demonstrate strong accuracy and interpretability. In the second part, I will talk about more broadly the intersection of AI and Science, including science for AI (Poisson Flow Generative Models), science of AI (understanding grokking), and AI for Science (AI scientists).