Institute for Pure & Applied Mathematics (IPAM) · Science

Institute for Pure & Applied Mathematics (IPAM)

The Institute for Pure and Applied Mathematics (IPAM) is a National Science Foundation Math Institute at the University of California, Los Angeles (UCLA) that fosters the interaction of mathematics with a broad range of science and technology, builds new interdisciplinary research communities, promotes mathematical innovation, and engages and transforms the world through mathematics. IPAM fulfills its mission through workshops and programs that connect mathematics and other disciplines or multiple areas of mathematics. These activities bring in thousands of visitors annually from academia, government, and industry. The NSF has encouraged IPAM to make the scientific presentations of our speakers available to a wider audience. While this YouTube channel contains many of our most popular videos, our full video archive is available at www.ipam.ucla.edu/videos.

Institute for Pure & Applied Mathematics (IPAM)

Episodes

Jelena Bradic: "Causality and machine learning for scientific discovery"

Marina Meilă: "Validation and Reproducibility by Geometry, for Unsupervised Learning"

John Maddocks: "The cgDNA sequence-dependent coarse-grain model of dsDNA: Bridging the scales fr..."

Gitta Kutyniok: "An Information Theoretic Approach to Validate Deep Learning-Based Algorithms"

Samory Kpotufe: "Some New Insights On Transfer Learning"

Klaus-Robert Müller: "Understanding Machine Learning Models"

Maziar Raissi: "Hidden Physics Models: Machine Learning of Non-Linear Partial Differential Equat..."

Paris Perdikaris: "Overcoming gradient pathologies in constrained neural networks"

Jens Eisert: "Learning dynamical laws from data in classical and quantum settings"

Jean-Christophe Loiseau: "Chaotic convection and Lorenz-like dynamics/A brief overview of SINDy"

Steve Brunton: "Discovering interpretable and generalizable dynamical systems from data"

Boumediene Hamzi: "Machine Learning and Dynamical Systems meet in Reproducing Kernel Hilbert Spaces"

Krithika Manohar: "Kernel Analog Forecasting: Multiscale Problems"

Mohammad Farazmand: "Accelerated Gradient Optimization: A Multiscale Analysis"

Petros Koumoutsakos: "Machine Learning for Fluid Mechanics"

Tristan Bereau: "Physics in and out of machine learning for molecular simulations: priors and pr..."

Francesco Paesani: "Data-driven models for predictive molecular simulations"

Pratyush Tiwary: "Learning to learn, learning to forget"

Stephan Hoyer: "Improving PDE solvers and PDE-constrained optimization with deep learning and di..."

Zachary Lipton: "Interpretability: of what, for whom, why, and how?"