Data files for "Neural reparameterization improves structural optimization"
Stephan Hoyer, Jascha Sohl‐Dickstein, Sam Greydanus · arXiv (Cornell University) · 2019
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.
Cited by 54 works. doi:10.48550/arxiv.1909.04240 Open-access PDF
Authors
References
- On the limited memory BFGS method for large scale optimization
- Image Style Transfer Using Convolutional Neural Networks
- Topology Optimization: Theory, Methods, and Applications
- The method of moving asymptotes—a new method for structural optimization
- Updating Quasi-Newton Matrices with Limited Storage
- Optimization of Structural Topology, Shape, and Material
- Numerical instabilities in topology optimization: A survey on procedures dealing with checkerboards, mesh-dependencies and local minima
- A 99 line topology optimization code written in Matlab
- Algorithm 887
- A review of the adjoint-state method for computing the gradient of a functional with geophysical applications