arXiv · 2011.14057
Multidimensional Persistence Module Classification via Lattice-Theoretic Convolutions
Abstract
Multiparameter persistent homology has been largely neglected as an input to machine learning algorithms. We consider the use of lattice-based convolutional neural network layers as a tool for the analysis of features arising from multiparameter persistence modules. We find that these show promise as an alternative to convolutions for the classification of multidimensional persistence modules.
Explore related subjects
Keep this discovery
Hans Riess, Jakob Hansen, Robert Ghrist. 2020-11-28. Multidimensional Persistence Module Classification via Lattice-Theoretic Convolutions. https://arxiv.org/abs/2011.14057
Cite the original work for its findings. Save a collection to share your selection of sources.