English

Can neural networks learn persistent homology features?

Machine Learning 2020-12-01 v1 Algebraic Topology

Abstract

Topological data analysis uses tools from topology -- the mathematical area that studies shapes -- to create representations of data. In particular, in persistent homology, one studies one-parameter families of spaces associated with data, and persistence diagrams describe the lifetime of topological invariants, such as connected components or holes, across the one-parameter family. In many applications, one is interested in working with features associated with persistence diagrams rather than the diagrams themselves. In our work, we explore the possibility of learning several types of features extracted from persistence diagrams using neural networks.

Keywords

Cite

@article{arxiv.2011.14688,
  title  = {Can neural networks learn persistent homology features?},
  author = {Guido Montúfar and Nina Otter and Yuguang Wang},
  journal= {arXiv preprint arXiv:2011.14688},
  year   = {2020}
}

Comments

Topological Data Analysis and Beyond Workshop at the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada

R2 v1 2026-06-23T20:35:40.753Z