CMSA Conference on Mathematics in Science: Perspectives and Prospects 10/28/2023
Speaker: Mike Freedman (Harvard CMSA)
Title: ML, QML, and Dynamics: What mathematics can help us understand and advance machine learning?
Abstract: Vannila deep neural nets DNN repeatedly stretch and fold. They are reminiscent of the logistic map and the Smale horseshoe. What kind of dynamics is responsible for their expressivity and trainability. Is chaos playing a role? Is the Kolmogorov Arnold representation theorem relevant? Large language models are full of linear maps. Might we look for emergent tensor structures in these highly trained maps in analogy with emergent tensor structures at local minima of certain loss functions in high-energy physics.
Негізгі бет Ғылым және технология Mike Freedman | ML, QML, and Dynamics: What mathematics can help us understand...
Пікірлер