Can I read A Topology Layer for Machine Learning on EtoBox?

A Topology Layer for Machine Learning by Brüel-Gabrielsson, Rickard; Nelson, Bradley J.; Dwaraknath, Anjan; Skraba, Primoz; Guibas, Leonidas J.; Carlsson, Gunnar is a scholarly article available to read on EtoBox.

What is A Topology Layer for Machine Learning about?

Topology applied to real world data using persistent homology has started to find applications within machine learning, including deep learning. We present a differentiable topology layer that computes persistent homology based on level set filtrations and edge-based filtrations. We present three novel applications: the topological layer can (i) regularize data reconstruction or the weights of machine learning models, (ii) construct a loss on the output of a deep generative network to incorporate topological priors, and (iii) perform topological adversarial attacks on deep networks trained with persistence features. The code (www.github.com/bruel-gabrielsson/TopologyLayer) is publicly available and we hope its availability will facilitate the use of persistent homology in deep learning and other gradient based applications.

Author

Brüel-Gabrielsson, Rickard; Nelson, Bradley J.; Dwaraknath, Anjan; Skraba, Primoz; Guibas, Leonidas J.; Carlsson, Gunnar

Published

2019

Language

EN