Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Herrmann, Leon, Sigmund, Ole, Li, Viola Muning, Vogl, Christian, Kollmannsberger, Stefan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2407.17957
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917733108547584
author Herrmann, Leon
Sigmund, Ole
Li, Viola Muning
Vogl, Christian
Kollmannsberger, Stefan
author_facet Herrmann, Leon
Sigmund, Ole
Li, Viola Muning
Vogl, Christian
Kollmannsberger, Stefan
contents Neural networks have recently been employed as material discretizations within adjoint optimization frameworks for inverse problems and topology optimization. While advantageous regularization effects and better optima have been found for some inverse problems, the benefit for topology optimization has been limited -- where the focus of investigations has been the compliance problem. We demonstrate how neural network material discretizations can, under certain conditions, find better local optima in more challenging optimization problems, where we here specifically consider acoustic topology optimization. The chances of identifying a better optimum can significantly be improved by running multiple partial optimizations with different neural network initializations. Furthermore, we show that the neural network material discretization's advantage comes from the interplay with the Adam optimizer and emphasize its current limitations when competing with constrained and higher-order optimization techniques. At the moment, this discretization has only been shown to be beneficial for unconstrained first-order optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2407_17957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Neural Networks for Generating Better Local Optima in Topology Optimization
Herrmann, Leon
Sigmund, Ole
Li, Viola Muning
Vogl, Christian
Kollmannsberger, Stefan
Machine Learning
Neural networks have recently been employed as material discretizations within adjoint optimization frameworks for inverse problems and topology optimization. While advantageous regularization effects and better optima have been found for some inverse problems, the benefit for topology optimization has been limited -- where the focus of investigations has been the compliance problem. We demonstrate how neural network material discretizations can, under certain conditions, find better local optima in more challenging optimization problems, where we here specifically consider acoustic topology optimization. The chances of identifying a better optimum can significantly be improved by running multiple partial optimizations with different neural network initializations. Furthermore, we show that the neural network material discretization's advantage comes from the interplay with the Adam optimizer and emphasize its current limitations when competing with constrained and higher-order optimization techniques. At the moment, this discretization has only been shown to be beneficial for unconstrained first-order optimization.
title Neural Networks for Generating Better Local Optima in Topology Optimization
topic Machine Learning
url https://arxiv.org/abs/2407.17957