17 citations · 27 across the 11 of their papers we have counts for
14 papers
Decorrelating neurons using persistence
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. For this, we present two regularisation terms c…
A topological classifier to characterize brain states: When shape matters more than variance
Aina Ferrà, Gloria Cecchini, Fritz-Pere Nobbe Fisas +2
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 i…
Importance attribution in neural networks by means of persistence landscapes of time series
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.…
Predicting the generalization gap in neural networks using topological data analysis
Rubén Ballester, Xavier Arnal Clemente, Carles Casacuberta +3
Understanding how neural networks generalize on unseen data is crucial for designing more robust and reliable models. In this paper, we study the generalization gap of neural netwo…
Reconstruction of univariate functions from directional persistence diagrams
Aina Ferrà, Carles Casacuberta, Oriol Pujol
We describe a method for approximating a single-variable function using persistence diagrams of sublevel sets of from height functions in different directions. We provide a…
Combinatorial homotopy categories
Carles Casacuberta, Jiri Rosicky
A model category is called combinatorial if it is cofibrantly generated and its underlying category is locally presentable. As shown in recent years, homotopy categories of combina…