Topological measurement of deep neural networks using persistent homology

DOI10.1007/s10472-021-09761-3OpenAlexW3089808853MaRDI QIDQ2075369

Satoru Watanabe, Hayato Yamana

Publication date: 14 February 2022

Published in: Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2106.03016

zbMATH Keywords

topological data analysispersistent homologydeep neural networkconvolutional neural network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Persistent homology and applications, topological data analysis (55N31)

Uses Software

• Gudhi
• javaPlex
• MNIST
• Python
• TensorFlow
• CIFAR
• Hyperopt
• SVCCA

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• The Simplex Tree: An Efficient Data Structure for General Simplicial Complexes
• Cliques and cavities in the human connectome
• Topological persistence and simplification
• A topological measurement of protein compressibility
• javaPlex: A Research Software Package for Persistent (Co)Homology
• What can topology tell us about the neural code?
• Persistent homology of complex networks

This page was built for publication: Topological measurement of deep neural networks using persistent homology