SKM 2023 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

DY: Fachverband Dynamik und Statistische Physik

DY 11: Focus Session: Physics Meets ML II – Understanding Machine Learning as Complex Interacting Systems (joint session DY/TT)

DY 11.6: Invited Talk

Monday, March 27, 2023, 17:30–18:00, ZEU 250

Deep Learning Theory Beyond the Kernel Limit — •Cengiz Pehlevan — Harvard University, USA

Deep learning has emerged as a successful paradigm for solving challenging machine learning and computational problems across a variety of domains. However, theoretical understanding of the training and generalization of modern deep learning methods lags behind current practice. I will give an overview of our recent results in this domain, including a new theory that we derived by applying dynamical field theory to deep learning dynamics. This theory gives insight into internal representations learned by the network under different learning rules.