Rubén Ballester, Carles Casacuberta, Sergio Escalera
Topological data analysis for neural network analysis: A comprehensive survey
arXiv:2312.05840 (December 2023)
Rubén Ballester, Carles Casacuberta, Sergio Escalera
Decorrelating neurons using persistence
NeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations
Proceedings of Machine Learning Research (2023), open access
openreview.net/forum?id=NJS6568y79
Ferrà A, Cecchini G, Nobbe Fisas F-P, Casacuberta C, Cos I (2023)
A topological classifier to characterize brain states: When shape matters more than variance
PLoS ONE 18(10): e0292049, open access
DOI:10.1371/journal.pone.0292049
Ferrà, A., Casacuberta, C., Pujol, O.
Importance attribution in neural networks by means of persistence landscapes of time series
Neural Computing and Applications 35, 20143-20156 (2023), open access
DOI:10.1007/s00521-023-08731-6
Aina Ferrà, Carles Casacuberta, Oriol Pujol
Reconstruction of univariate functions from directional persistence diagrams
arXiv:2203.01894 (v1: March 2022; v2: February 2023)
Rubén Ballester, Xavier Arnal Clemente, Carles Casacuberta, Meysam Madadi, Ciprian A. Corneanu, Sergio Escalera
Predicting the generalization gap in neural networks using topological data analysis
Neurocomputing (2024), to appear
arXiv:2203.12330 (v1: March 2022; v2: August 2023)