5 papers
OPAL: Orthonormal Prototype Alignment Learning for Interpretable Image Classification
Ilán Carretero, Gustavo Jesús Angulo, Rocío del Amor +1
Prototypical part-based models provide explainable predictions by comparing input regions to learned prototypes. However, current approaches are burdened by complex, multi-stage tr…
Choosing a parallel heterogeneous ensemble method for tabular classification
Vassili Maillet, Gustavo, Angulo +1
Parallel ensemble methods were compared on small-to-medium tabular classification tasks drawn from OpenML CC18. A set of ``best practice'' recommendations on the use of ensemb…
Morphological Representation Theory in the Fourier Inf-Semilattice: Universal Decomposition of Frequency-Domain Deep Learning Operators
Gustavo, Angulo
We develop a morphological representation theory for operators acting in the frequency domain of . Equipping the space with the \emph{Fourier inf-semilattice} or…
Lattice theory and algebraic models for deep convolutional learning based on mathematical morphology
Gustavo, Angulo
We develop a rigorous algebraic framework for deep convolutional architectures, CNNs, ResNets, and encoder--decoder networks such as UNet, grounded in lattice theory and mathematic…
Approximating Condorcet Ordering for Vector-valued Mathematical Morphology
Marcos Eduardo Valle, Santiago Velasco-Forero, Joao Batista Florindo +1
Mathematical morphology provides a nonlinear framework for image and spatial data processing and analysis. Although there have been many successful applications of mathematical mor…