On the feasibility of small-data learning in simulation-driven engineering tasks with known mechanisms and effective data representations
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.
PDF Abstract