Poster
in
Workshop: Machine Learning and the Physical Sciences
NLP Inspired Training Mechanics For Modeling Transient Dynamics
Lalit Ghule · Rishikesh Ranade · Jay Pathak
Abstract:
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%.
Chat is not available.