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 physicsInsights on gradient-based algorithms in high-dimensional learningFeature Learning in Infinite-Width Neural NetworksWeak Supervision for the Strong ForceImplicit Regularization in Quantum Tensor NetworksBuilding symmetries into generative flow modelsMachine Learning for Calabi-Yau metricsNeural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning DynamicsAlgebraic Neural NetworksHarnessing Data Revolution in Quantum MatterScience is a verb: adopting the scientific method and best practices in AI researchFast and Credible Inference with Truncated Marginal Neural Ratio EstimationSimulation-based inference for astrophysical dark matter searchesExplorations at the Physics ∩ ML InterfaceCompositionality of Symmetry in Equivariant Multilayer PerceptronsDiscovering new phases of matter with unsupervised and interpretable support vector machinesEquivariant Neural Fields: A Roadmap Towards Generalizable Neural Representation and InferenceUncovering the Unknowns of Deep Neural Networks: Challenges and OpportunitiesA Mathematical Exploration of Why Language Models Help Solve Downstream TasksQuantum Machine Learning in High Energy Physics