52:24

Jonas Buchli & Federico Felici: Magnetic control of tokamak plasmas with deep reinforcement learning

36:36

Arvind Neelakantan: Text and Code Embeddings

52:52

Séamus Davis: Machine learning in electronic-quantum-matter imaging experiments

58:01

Mikhail Belkin: From classical statistics to modern deep learning

50:32

Eliu Huerta: AI for Science: Let’s talk business

01:10:52

Bin Yu: Interpreting Deep Neural Networks towards Trustworthiness

01:12:47

Sonia Contera: It from bit? The future of bioinspired computing beyond ML

01:01:24

Huilin Qu: Jet Tagging in the Era of Deep Learning

57:15

Stéphane Mallat: Hamiltonian Estimations by Conditional Renormalisation Group and Convolution Nets

01:18:06

Craig Mundie: Artificial General Intelligence - The Advent of Polymathic Machines

01:00:22

Nathan Kutz: The Future of Governing Equations

01:21:31

Tim Green: Highly accurate protein structure prediction with AlphaFold

46:04

Ricardo Vinuesa: Artificial Intelligence, Computational Fluid Dynamics, and Sustainability

01:14:43

Andrew Stuart: Learning Solution Operators for PDEs

01:00:26

Rachel Prudden: Probabilistic modelling for atmospheric science: beyond the noise

56:25

Laure Zanna: Climate Modeling in the Age of Machine Learning

58:10

Tom Andersson: Seasonal Arctic sea ice forecasting with probabilistic deep learning

59:35

Adrien Gaidon: Self-supervised 3D vision

01:33:07

Steve Oberlin: HPC + AI: How Learned Models Are Revolutionizing Scientific Simulation

01:08:38

David Spergel: Determining the Universe’s Initial Conditions

53:52

Lode Pollet: Discovering new phases of matter with unsupervised and interpretable SVMs

01:08:36

Michael Kagan: Generative Model Based Design Optimization and Unfolding

01:03:31

Sofia Vallecorsa: Quantum Machine Learning in High Energy Physics

01:15:06

Ard Louis: Deep neural networks have an inbuilt Occam’s razor

01:18:23

Jascha Sohl-Dickstein: Understanding overparameterized neural networks

01:11:23

Atılım Güneş Baydin: Probabilistic Programming for Inverse Problems in the Physical Sciences

01:08:29

Roger Melko: Reconstructing quantum states with generative models

01:00:33

Phiala Shanahan: Provably exact sampling for first-principles theoretical physics

59:29

Victor Bapst: Unveiling the predictive power of static structure in glassy systems

59:30

Giuseppe Carleo: Many-body quantum wave functions in the era of machine learning

01:30:05

Max Tegmark: AI for physics & physics for AI

59:49

Guillaume Lample: Deep Learning for Symbolic Mathematics

57:12

Maurizio Pierini: Doing more with less: Deep Learning for Physics at the Large Hadron Collider

01:02:16

Shirley Ho: What can Deep Learning help in addressing Astrophysical Challenges

58:55

Brian Spears: Cognitive Simulation: combining simulation and experiment with artificial intelligence

56:13

Peter Dueben: Machine learning for weather predictions

51:14

Ben Nachman: Extracting the most from collider data with deep learning

51:34

Peter Hatfield: Extreme Physics, Extreme Data

38:03

Mike Walmsley: Galaxy Zoo(m): Probabilistic Galaxy Morphology via Bayesian CNNs and Active Learning