no code implementations • 22 Mar 2024 • Rocio Gonzalez-Diaz, Miguel A. Gutiérrez-Naranjo, Eduardo Paluzo-Hidalgo
In this paper, we present SIMAP, a novel layer integrated into deep learning models, aimed at enhancing the interpretability of the output.
no code implementations • 4 Jun 2023 • Álvaro Torras-Casas, Eduardo Paluzo-Hidalgo, Rocio Gonzalez-Diaz
Data quality is crucial for the successful training, generalization and performance of artificial intelligence models.
1 code implementation • 29 May 2023 • Eduardo Paluzo-Hidalgo, Miguel A. Gutiérrez-Naranjo, Rocio Gonzalez-Diaz
In this paper, we overcome these issues by proposing an SMNN training procedure based on a support subset of the given dataset and replacing the construction of the convex polytope by a method based on projections to a hypersphere.
1 code implementation • 26 Oct 2021 • Eduardo Paluzo-Hidalgo, Guillermo Aguirre-Carrazana, Rocio Gonzalez-Diaz
The automatic recognition of a person's emotional state has become a very active research field that involves scientists specialized in different areas such as artificial intelligence, computer vision or psychology, among others.
no code implementations • 19 Dec 2019 • Eduardo Paluzo-Hidalgo, Rocio Gonzalez-Diaz, Miguel A. Gutiérrez-Naranjo
In this paper, we use topological data analysis (TDA) tools such as persistent homology, persistent entropy and bottleneck distance, to provide a {\it TDA-based summary} of any given set of texts and a general method for computing a distance between any two literary styles, authors or periods.
no code implementations • 26 Jul 2019 • Rocio Gonzalez-Diaz, Miguel A. Gutiérrez-Naranjo, Eduardo Paluzo-Hidalgo
This approach is based on an approximation of continuous functions by simplicial maps.
no code implementations • 11 Apr 2019 • Javier Lamar-Leon, Rocio Gonzalez-Diaz, Edel Garcia-Reyes
In this paper, we present an algorithm that computes the topological signature for a given periodic motion sequence.
1 code implementation • 20 Mar 2019 • Rocio Gonzalez-Diaz, Miguel A. Gutiérrez-Naranjo, Eduardo Paluzo-Hidalgo
We prove that the accuracy of the learning process of a neural network on a representative dataset is "similar" to the accuracy on the original dataset when the neural network architecture is a perceptron and the loss function is the mean squared error.
no code implementations • 3 Jan 2018 • Rocio Gonzalez-Diaz, Maria-Jose Jimenez, Belen Medrano
In this paper, taking as input a time-varying sequence of two-dimensional (2D) binary digital images, we develop an algorithm for encoding, in the so-called {\it spatiotemporal barcode}, lifetime of connected components (of either the foreground or background) that are moving in the image sequence over time (this information may not coincide with the one provided by the persistence barcode).
no code implementations • 14 Mar 2014 • Guillaume Damiand, Rocio Gonzalez-Diaz, Samuel Peltier
In this paper, we show that contraction operations preserve the homology of $n$D generalized maps, under some conditions.
no code implementations • 12 Mar 2014 • Rocio Gonzalez-Diaz, Maria-Jose Jimenez, Belen Medrano
A binary three-dimensional (3D) image $I$ is well-composed if the boundary surface of its continuous analog is a 2D manifold.