Multidimensional Persistence Module Classification via Lattice-Theoretic Convolutions

11/28/2020
by   Hans Riess, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset