Neural reparameterization improves structural optimization Article Swipe

PDF

Related Concepts

Computer science Parameterized complexity Artificial neural network Bridge (graph theory) Grid Truss Hyperparameter optimization Mathematical optimization Baseline (sea) Algorithm Artificial intelligence Mathematics Engineering Structural engineering Support vector machine Geometry Medicine Geology Internal medicine Oceanography

Stephan Hoyer , Jascha Sohl‐Dickstein , Sam Greydanus ·

YOU? · · 2019 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1909.04240 · OA: W2972419151

Structural optimization is a popular method for designing objects such as bridge trusses, airplane wings, and optical devices. Unfortunately, the quality of solutions depends heavily on how the problem is parameterized. In this paper, we propose using the implicit bias over functions induced by neural networks to improve the parameterization of structural optimization. Rather than directly optimizing densities on a grid, we instead optimize the parameters of a neural network which outputs those densities. This reparameterization leads to different and often better solutions. On a selection of 116 structural optimization tasks, our approach produces the best design 50% more often than the best baseline method.