NTopo: Mesh-free Topology Optimization using Implicit Neural Representations - NeurIPS 2021

  Рет қаралды 738

Computational Robotics Lab

Computational Robotics Lab

Күн бұрын

Recent advances in implicit neural representations show great promise when it comes to generating numerical solutions to partial differential equations. Compared to conventional alternatives, such representations employ parameterized neural networks to define, in a mesh-free manner, signals that are highly-detailed, contin- uous, and fully differentiable. In this work, we present a novel machine learning approach for topology optimization-an important class of inverse problems with high-dimensional parameter spaces and highly nonlinear objective landscapes. To effectively leverage neural representations in the context of mesh-free topology optimization, we use multilayer perceptrons to parameterize both density and dis- placement fields. Our experiments indicate that our method is highly competitive for minimizing structural compliance objectives, and it enables self-supervised learning of continuous solution spaces for topology optimization problems.
Jonas Zehnder
jzehnder.me/
Yue Li
liyuesolo.gith...
Stelian Coros
crl.ethz.ch/cor...
Bernhard Thomaszewski
n.ethz.ch/~bth...

Пікірлер
Thank you mommy 😊💝 #shorts
0:24
5-Minute Crafts HOUSE
Рет қаралды 33 МЛН
Hilarious FAKE TONGUE Prank by WEDNESDAY😏🖤
0:39
La La Life Shorts
Рет қаралды 44 МЛН
Making STRONG shelves with Topology Optimization
14:15
Made with Layers (Thomas Sanladerer)
Рет қаралды 1,4 МЛН
Free Topology Optimization for everybody - Inspire Personal 2023
15:05
Dr.-Ing. Manuel Ramsaier
Рет қаралды 6 М.
Topology Optimization using RocketML Deep Learning
27:10
RocketML
Рет қаралды 2,7 М.
Backpropagation Details Pt. 1: Optimizing 3 parameters simultaneously.
18:32
StatQuest with Josh Starmer
Рет қаралды 220 М.
FreeCAD: All About Analysis And Editing STL/Mesh Models |JOKO ENGINEERING|
19:58