Physics ∩ ML
a virtual hub at the interface of theoretical physics and deep learning.
Neural Scaling Laws and GPT-3
Jared Kaplan, Johns Hopkins University, 12:00 EDT
Flow-based likelihoods for non-Gaussian inference.
Ana Diaz Rivero, Harvard University, 12:00 EDT
Euclidean Neural Networks: Adventures in learning with 3D geometry and geometric tensors.
Tess Smidt, Lawrence Berkeley Laboratory, 12:00 EDT
Harnessing Data Revolution in Quantum Matter.
Eun-Ah Kim, Cornell University, 12:00 EDT
Sofia Vallecorsa, CERN, 12:00 EDT
Michelle Ntampaka, Space Telescope Science Institute, 12:00 EDT
Machine learning as a discovery tool in hep-th
Vishnu Jejjala, University of Witwatersrand, 12:00 EDT
Science is a verb: adopting the scientific method and best practices in AI research
Michela Paganini, Facebook AI Research, 12:00 EDT
Insights on gradient-based algorithms in high-dimensional learning
Lenka Zdeborova, EPFL, 12:00 EDT
The large learning rate phase of deep learning
Yasaman Bahri, Google Brain, 12:00 EDT
Discovering new phases of matter with unsupervised and interpretable support vector machines
Lode Pollet, LMU Munich, 12:00 EDT
Discovering Symbolic Models in Physical Systems using Deep Learning
Shirley Ho, Flatiron Institute, 12:00 EDT
Next page →
For link and password to the talks, please sign up for the
Physics ∩ ML mailing list
Videos may be found on
our YouTube channel
and slides by clicking on past talk titles.
About Physics ∩ ML