Normalizing Flows for scientific applications
Uros Seljak, UC Berkeley
Видео Normalizing Flows for scientific applications канала Physics Meets ML
Видео Normalizing Flows for scientific applications канала Physics Meets ML
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Anomaly detection in the search for new physics
Insights on gradient-based algorithms in high-dimensional learning
Feature Learning in Infinite-Width Neural Networks
Weak Supervision for the Strong Force
Implicit Regularization in Quantum Tensor Networks
Building symmetries into generative flow models
Machine Learning for Calabi-Yau metrics
Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics
Algebraic Neural Networks
Harnessing Data Revolution in Quantum Matter
Science is a verb: adopting the scientific method and best practices in AI research
Fast and Credible Inference with Truncated Marginal Neural Ratio Estimation
Simulation-based inference for astrophysical dark matter searches
Explorations at the Physics ∩ ML Interface
Compositionality of Symmetry in Equivariant Multilayer Perceptrons
Discovering new phases of matter with unsupervised and interpretable support vector machines
Equivariant Neural Fields: A Roadmap Towards Generalizable Neural Representation and Inference
Uncovering the Unknowns of Deep Neural Networks: Challenges and Opportunities
A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks
Quantum Machine Learning in High Energy Physics