AI Paper Atlas

Research map / Architectures and efficiency / CNN design

DNN-based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel

Benjamin Dupuis, Arthur Jacot

NeurIPS 2021 · Architectures and efficiency › CNN design · approach: Invertible and wide-network analysis · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add a torus embedding of the input coordinates before the networkDNN density-field topology optimisation · topology optimisation with applied forcesrespect of force symmetry / translation and rotation invariance (qualitative)Improved
use ReLU activation instead of cosine activation with the torus embedding (ablation)torus-embedded network · topology optimisationfilter radius / shape precisionHurt
change the filter radius R_1/2 of the limiting NTKembedded DNN · final shape geometryshape complexity (holes, high frequencies)Mixed
train without an embedding and upsample the density field (ablation)ReLU FCNN with batchnorm · upsampling of density fieldvisual artifactsHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy