Data efficient surrogate modeling for engineering design: Ensemble-free batch mode deep active learning for regression
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911290489831424 |
|---|---|
| author | Kapoor, Sarthak Vardhan, Harsh Timalsina, Umesh Kumar, Sumit Volgyesi, Peter Sztipanovits, Janos |
| author_facet | Kapoor, Sarthak Vardhan, Harsh Timalsina, Umesh Kumar, Sumit Volgyesi, Peter Sztipanovits, Janos |
| contents | High fidelity design evaluation processes such as Computational Fluid Dynamics and Finite Element Analysis are often replaced with data driven surrogates to reduce computational cost in engineering design optimization. However, building accurate surrogate models still requires a large number of expensive simulations. To address this challenge, we introduce epsilon HQS, a scalable active learning strategy that leverages a student teacher framework to train deep neural networks efficiently. Unlike Bayesian AL methods, which are computationally demanding with DNNs, epsilon HQS selectively queries informative samples to reduce labeling cost. Applied to CFD, FEA, and propeller design tasks, our method achieves higher accuracy under fixed labeling cost budgets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_10360 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Data efficient surrogate modeling for engineering design: Ensemble-free batch mode deep active learning for regression Kapoor, Sarthak Vardhan, Harsh Timalsina, Umesh Kumar, Sumit Volgyesi, Peter Sztipanovits, Janos Machine Learning Artificial Intelligence Numerical Analysis High fidelity design evaluation processes such as Computational Fluid Dynamics and Finite Element Analysis are often replaced with data driven surrogates to reduce computational cost in engineering design optimization. However, building accurate surrogate models still requires a large number of expensive simulations. To address this challenge, we introduce epsilon HQS, a scalable active learning strategy that leverages a student teacher framework to train deep neural networks efficiently. Unlike Bayesian AL methods, which are computationally demanding with DNNs, epsilon HQS selectively queries informative samples to reduce labeling cost. Applied to CFD, FEA, and propeller design tasks, our method achieves higher accuracy under fixed labeling cost budgets. |
| title | Data efficient surrogate modeling for engineering design: Ensemble-free batch mode deep active learning for regression |
| topic | Machine Learning Artificial Intelligence Numerical Analysis |
| url | https://arxiv.org/abs/2211.10360 |