Workshops

Learning molecular model from simulation and experimental data

No equations, no variables, no space and no time: data driven models and gauge-invariant data mining

Why Deep Learning Works: Heavy-Tailed Random Matrix Theory as an Example of Physics Informed Machine Learning

Simulating the Universe with Deep Learning

Model Interpretability for Building Confidence and Sparking Insight in Scientific Applications

Machine learning based multi-scale modeling

Maximum Entropy Methods for Combining Physics-Based Simulation with Empirical Data

Molecular design blueprints: materials and catalysts from new simulation and machine learning tools

Universal Probabilistic Programming in Simulators

Planning Chemical Syntheses with Deep Neural Networks and Discipline Scale Data

Coordinates, governing equations and limits of model discovery

Accelerating Scientific Discovery through Interpretable Machine Learning and Intelligent Experimentation

Learning structured models of physics

Interpretability and explainability from a causal lens

Structured Deep Generative Models

Can we machine learn drug discovery?

Deep Learning Dive into the Scanning Transmission Electron Microscopy: Materials Design, Learning Physics, and Atomic Manipulation

Quantum Machine Learning

Density functionals from machine learning

Simulation-based inference, interpretability, and experimental design

Interpretability: of what, for whom, why, and how?

Improving PDE solvers and PDE-constrained optimization with deep learning and differentiable programming

Learning to learn, learning to forget

Machine learning of protein folding funnels from experimental data and construction of latent space molecular simulators

Data-driven models for predictive molecular simulations

Physics in and out of machine learning for molecular simulations: priors and predictive constraints