CupNet – Pruning a network for geometric data

05/11/2020

∙

Using data from a simulated cup drawing process, we demonstrate how the inherent geometrical structure of cup meshes can be used to effectively prune an artificial neural network in a straightforward way.

READ FULL TEXT

CupNet – Pruning a network for geometric data

Artificial Neural Network evaluation of Poincaré constant for Voronoi polygons

The Incredible Shrinking Neural Network: New Perspectives on Learning Representations Through The Lens of Pruning

Signature Verification using Geometrical Features and Artificial Neural Network Classifier

Growing Artificial Neural Networks

Enhancing the Regularization Effect of Weight Pruning in Artificial Neural Networks

Treebar Maps: Schematic Representation of Networks at Scale

Fast and accurate numerical simulations for the study of coronary artery bypass grafts by artificial neural network

CupNet – Pruning a network for geometric data

Related Research

Artificial Neural Network evaluation of Poincaré constant for Voronoi polygons

The Incredible Shrinking Neural Network: New Perspectives on Learning Representations Through The Lens of Pruning

Signature Verification using Geometrical Features and Artificial Neural Network Classifier

Growing Artificial Neural Networks

Enhancing the Regularization Effect of Weight Pruning in Artificial Neural Networks

Treebar Maps: Schematic Representation of Networks at Scale

Fast and accurate numerical simulations for the study of coronary artery bypass grafts by artificial neural network