On the Feasibility of Small-Data Learning in Simulation-Driven Engineering Tasks with Known Mechanisms and Effective Data Representations
Abstract
The application of machine learning (ML) in scientific tasks is increasing, especially ML in simulation-driven engineering tasks. While previous studies were mostly model-centric and required large-data learning, recent studies start to pay attention to data-centric AI and are investigating small-data learning with effective structured representations, which is significant for industrial application. This article provides a theoretical discussion for the feasibility of small-data learning with structured representations, which is then verified through the surrogate modelling of hot stamping simulations. Future directions are also discussed.
Cite
Text
Zhou et al. "On the Feasibility of Small-Data Learning in Simulation-Driven Engineering Tasks with Known Mechanisms and Effective Data Representations." NeurIPS 2021 Workshops: AI4Science, 2021.Markdown
[Zhou et al. "On the Feasibility of Small-Data Learning in Simulation-Driven Engineering Tasks with Known Mechanisms and Effective Data Representations." NeurIPS 2021 Workshops: AI4Science, 2021.](https://mlanthology.org/neuripsw/2021/zhou2021neuripsw-feasibility/)BibTeX
@inproceedings{zhou2021neuripsw-feasibility,
title = {{On the Feasibility of Small-Data Learning in Simulation-Driven Engineering Tasks with Known Mechanisms and Effective Data Representations}},
author = {Zhou, Haosu and Attar, Hamid Reza and Pan, Yue and Li, Xuetao and Childs, Peter R N and Li, Nan},
booktitle = {NeurIPS 2021 Workshops: AI4Science},
year = {2021},
url = {https://mlanthology.org/neuripsw/2021/zhou2021neuripsw-feasibility/}
}