no code implementations • 10 Dec 2023 • Rubén Ballester, Carles Casacuberta, Sergio Escalera
We discuss different strategies to obtain topological information from data and neural networks by means of TDA.
1 code implementation • 9 Aug 2023 • Rubén Ballester, Carles Casacuberta, Sergio Escalera
We propose a novel way to improve the generalisation capacity of deep learning models by reducing high correlations between neurons.
no code implementations • 7 Mar 2023 • Aina Ferrà, Gloria Cecchini, Fritz-Pere Nobbe Fisas, Carles Casacuberta, Ignasi Cos
Despite the remarkable accuracies attained by machine learning classifiers to separate complex datasets in a supervised fashion, most of their operation falls short to provide an informed intuition about the structure of data, and, what is more important, about the phenomena being characterized by the given datasets.
no code implementations • 6 Feb 2023 • Aina Ferrà, Carles Casacuberta, Oriol Pujol
We propose and implement a method to analyze time series with a neural network using a matrix of area-normalized persistence landscapes obtained through topological data analysis.
1 code implementation • 23 Mar 2022 • Rubén Ballester, Xavier Arnal Clemente, Carles Casacuberta, Meysam Madadi, Ciprian A. Corneanu, Sergio Escalera
Understanding how neural networks generalize on unseen data is crucial for designing more robust and reliable models.
no code implementations • 3 Mar 2022 • Aina Ferrà, Carles Casacuberta, Oriol Pujol
We describe a method for approximating a single-variable function $f$ using persistence diagrams of sublevel sets of $f$ from height functions in different directions.