Persistence-based operators in machine learning
Preprint
Abstract
Artificial neural networks can learn complex, salient data features to achieve a given task. On the opposite end of the spectrum, mathematically grounded methods such as topological data analysis allow users to design analysis pipelines fully aware of data constraints and symmetries. We introduce a class of persistence-based neural network layers. Persistence-based layers allow the users to easily inject knowledge about symmetries (equivariance) respected by the data, are equipped with learnable weights, and can be composed with state-of-the-art neural architectures.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Quod erat demonstrandum? - Towards a typology of the concept of explanation for the design of explainable AIExpert Systems with Applications, 2022
- Steady and ranging sets in graph persistenceJournal of Applied and Computational Topology, 2022
- Persistent-homology-based machine learning: a survey and a comparative studyArtificial Intelligence Review, 2022
- Complexes of tournaments, directionality filtrations and persistent homologyJournal of Applied and Computational Topology, 2021
- Bottleneck stability for generalized persistence diagramsProceedings of the American Mathematical Society, 2020
- Towards a topological–geometrical theory of group equivariant non-expansive operators for data analysis and machine learningNature Machine Intelligence, 2019
- The Theory of the Interleaving Distance on Multidimensional Persistence ModulesFoundations of Computational Mathematics, 2015
- Categorification of Persistent HomologyDiscrete & Computational Geometry, 2014
- A Mayer–Vietoris Formula for Persistent Homology with an Application to Shape Recognition in the Presence of OcclusionsFoundations of Computational Mathematics, 2011
- Stability of Persistence DiagramsDiscrete & Computational Geometry, 2006