NLP Inspired Training Mechanics For Modeling Transient Dynamics
Not on the map. Why?
Abstract (arXiv)
In recent years, Machine learning (ML) techniques developed for Natural Language Processing (NLP) have permeated into developing better computer vision algorithms. In this work, we use such NLP-inspired techniques to improve the accuracy, robustness and generalizability of ML models for simulating transient dynamics. We introduce teacher forcing and curriculum learning based training mechanics to model vortical flows and show an enhancement in accuracy for ML models, such as FNO and UNet by more than 50%.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 11 of its 14 references that are in the map. First posted on arXiv 4 Nov 2022.
Builds on
11 of 14 references.
References · 11
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
- 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 803
- 2018Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantificationcited by 199
- 2019Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networkscited by 145
- 2020EikoNet: Solving the Eikonal equation with Deep Neural Networkscited by 50
- 2020DiscretizationNet: A Machine-Learning based solver for Navier-Stokes Equations using Finite Volume Discretizationcited by 35
- 2019Unsupervised Deep Learning Algorithm for PDE-based Forward and Inverse Problemscited by 31
- 2022Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solverscited by 12
- 2022A composable machine-learning approach for steady-state simulations on high-resolution gridscited by 8
- 2021Stochastic Adversarial Koopman Model for Dynamical Systemscited by 4
Built on by
Citing papers per year: 2024: 1.
1 paper.