ICML 2024 Tutorial"Machine Learning on Function spaces скачать в хорошем качестве

ICML 2024 Tutorial"Machine Learning on Function spaces

ICML 2024 Tutorial "Machine Learning on Function spaces #NeuralOperators" Abstract: This tutorial will introduce neural operators, an extension of neural networks designed to learn mappings between infinite-dimensional function spaces. We'll cover the theoretical foundations, including their formulation and universal approximation capabilities. Emphasizing their discretization-invariance, we'll explore how neural operators tackle problems in partial differential equations (PDEs) and scientific computing tasks. This session is ideal for machine learning experts looking to leverage neural operators for advanced scientific and engineering applications. Speaker video:    • Speaker - ICML 2024 Tutorial"Machine Learn...   Slides video:    • Slides - ICML 2024 Tutorial"Machine Learni...   Slides PDF: https://drive.google.com/file/d/1uNRS... Reference: https://www.nature.com/articles/s4225... You may find the relevant papers: Neural Operator: Graph Kernel Network for Partial Differential Equations https://arxiv.org/pdf/2003.03485.pdf Multipole Graph Neural Operator for Parametric Partial Differential Equations https://arxiv.org/abs/2006.09535 Fourier Neural Operator for Parametric Partial Differential Equations https://arxiv.org/abs/2010.08895 Markov Neural Operators for Learning Chaotic Systems https://arxiv.org/abs/2106.06898 Neural Operator: Learning Maps Between Function Spaces https://arxiv.org/pdf/2108.08481.pdf Physics-Informed Neural Operator for Learning Partial Differential Equations https://arxiv.org/pdf/2111.03794.pdf U-NO: U-shaped Neural Operators https://arxiv.org/pdf/2204.11127.pdf Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs https://arxiv.org/pdf/2403.12553 Geometry-Informed Neural Operator for Large-Scale 3D PDEs https://arxiv.org/pdf/2309.00583 Blog posts: https://zongyi-li.github.io/blog/2020... https://zongyi-li.github.io/blog/2020... Library: https://github.com/neuraloperator