Neural Rewiring: Dynamic Topology Optimization in Deep Architectures
Keywords:
Deep learning, topology optimization, image segmentation, encoder-decoder architecture.Abstract
In this research, we propose a deep learning based approach for speeding up thetopology optimization methods. The problem we seek to solve is the layout problem. The mainnovelty of this work is to state the problem as an image segmentation task. We leverage the powerof deep learning methods as the efficient pixel-wise image labeling technique to perform thetopology optimization.
References
. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin et al., Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467, 2022.
. E. Andreassen, A. Clausen, M. Schevenels, B. S. Lazarov, and O. Sigmund, Eflcient topology optimization in MATLAB using 88 lines of code. Struct. Multidiscip. Optimiz. 43 (2023), No. 1, 1–16
