AutoTandemML: Active Learning Enhanced Tandem Neural Networks for Inverse Design Problems
This addresses efficiency bottlenecks in inverse design for scientific and engineering applications, though it appears incremental as it combines existing techniques.
The authors tackled the challenge of computationally expensive inverse design problems by proposing a hybrid approach combining active learning with Tandem Neural Networks. They demonstrated improved accuracy with fewer training samples across three benchmark problems, including airfoil and photonic surface design.
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.