AutoTandemML: Active Learning Enhanced Tandem Neural Networks for Inverse Design Problems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912240297312256 |
|---|---|
| author | Grbcic, Luka Müller, Juliane de Jong, Wibe Albert |
| author_facet | Grbcic, Luka Müller, Juliane de Jong, Wibe Albert |
| contents | Inverse design in science and engineering involves determining optimal design parameters that achieve desired performance outcomes, a process often hindered by the complexity and high dimensionality of design spaces, leading to significant computational costs. To tackle this challenge, we propose a novel hybrid approach that combines active learning with Tandem Neural Networks to enhance the efficiency and effectiveness of solving inverse design problems. Active learning allows to selectively sample the most informative data points, reducing the required dataset size without compromising accuracy. We investigate this approach using three benchmark problems: airfoil inverse design, photonic surface inverse design, and scalar boundary condition reconstruction in diffusion partial differential equations. We demonstrate that integrating active learning with Tandem Neural Networks outperforms standard approaches across the benchmark suite, achieving better accuracy with fewer training samples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15643 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AutoTandemML: Active Learning Enhanced Tandem Neural Networks for Inverse Design Problems Grbcic, Luka Müller, Juliane de Jong, Wibe Albert Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Neural and Evolutionary Computing Inverse design in science and engineering involves determining optimal design parameters that achieve desired performance outcomes, a process often hindered by the complexity and high dimensionality of design spaces, leading to significant computational costs. To tackle this challenge, we propose a novel hybrid approach that combines active learning with Tandem Neural Networks to enhance the efficiency and effectiveness of solving inverse design problems. Active learning allows to selectively sample the most informative data points, reducing the required dataset size without compromising accuracy. We investigate this approach using three benchmark problems: airfoil inverse design, photonic surface inverse design, and scalar boundary condition reconstruction in diffusion partial differential equations. We demonstrate that integrating active learning with Tandem Neural Networks outperforms standard approaches across the benchmark suite, achieving better accuracy with fewer training samples. |
| title | AutoTandemML: Active Learning Enhanced Tandem Neural Networks for Inverse Design Problems |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2502.15643 |