Enforcing constraints for interpolation and extrapolation in generative adversarial networks

DOI10.1016/j.jcp.2019.07.042zbMath1453.68159arXiv1803.08182OpenAlexW2794111629MaRDI QIDQ2222513

Enoch Yeung, Tobias Hagge, Panos Stinis, Alexandre M. Tartakovsky

Publication date: 27 January 2021

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1803.08182

zbMATH Keywords

predictiondynamical systemsextrapolationmachine learninggenerative adversarial networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of game theory (91A80) Numerical interpolation (65D05) Qualitative investigation and simulation of ordinary differential equation models (34C60) Neural nets and related approaches to inference from stochastic processes (62M45)

Related Items (6)

Symplectic neural networks in Taylor series form for Hamiltonian systems ⋮ Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems ⋮ Solving inverse-PDE problems with physics-aware neural networks ⋮ Mesh-Conv: convolution operator with mesh resolution independence for flow field modeling ⋮ Coercing machine learning to output physically accurate results ⋮ Enforcing Imprecise Constraints on Generative Adversarial Networks for Emulating Physical Systems

Uses Software

• TensorFlow
• torchdiffeq
• DGM

Cites Work

• Unnamed Item
• Stochastic global optimization as a filtering problem
• Problem reduction, renormalization, and memory
• Why does deep and cheap learning work so well?
• DGM: a deep learning algorithm for solving partial differential equations
• Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations
• Solving high-dimensional partial differential equations using deep learning
• Randomly distributed embedding making short-term high-dimensional data predictable
• Monte Carlo strategies in scientific computing

This page was built for publication: Enforcing constraints for interpolation and extrapolation in generative adversarial networks