Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics

This site last compiled Fri, 27 Oct 2023 17:07:25 +0000

Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE Dynamics Pingchuan Ma, Peter Yichen Chen, Bolei Deng, Joshua B. Tenenbaum, Tao Du, Chuang Gan, Wojciech Matusik Proceedings of the 40th International Conference on Machine Learning , PMLR 202:23279-23300, 2023. Abstract We propose a hybrid neural network (NN) and PDE approach for learning generalizable PDE dynamics from motion observations. Many NN approaches learn an end-to-end model that implicitly models both the governing PDE and constitutive models (or material models). Without explicit PDE knowledge, these a

saved by

• Umangi Jain

related reading

• proceedings.mlr.press/v202/ma23a/ma23a.pdfproceedings.mlr.press
• ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Biasproceedings.mlr.press
• Physics-Informed Diffusion Modelsarxiv.org
• On the Learnability of Physical Concepts: Can a Neural Network Understand What’s Real?arxiv.org
• Generative Image Dynamicsgenerative-dynamics.github.io
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• Statistical Mechanics of Deep Learningganguli-gang.stanford.edu
• Hamiltonian Neural PDE Solvers through Functional Approximationarxiv.org
• NL.pdfabehrouz.github.io
• Beyond Message Passing: a Physics-Inspired Paradigm for Graph Neural Networksthegradient.pub
• Physics-constrained machine learning for scientific computing - Amazon Scienceamazon.science
• [2608.13335] Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Lawsarxiv.org