1 code implementation • 15 Apr 2024 • Javier Perera-Lago, Víctor Toscano-Durán, Eduardo Paluzo-Hidalgo, Sara Narteni, Matteo Rucco
Machine learning algorithms are fundamental components of novel data-informed Artificial Intelligence architecture.
1 code implementation • 22 Mar 2024 • Víctor Toscano-Durán, Javier Perera-Lago, Eduardo Paluzo-Hidalgo, Rocío Gonzalez-Diaz, Miguel Ángel Gutierrez-Naranjo, Matteo Rucco
Finally, we experimentally compare how these data reduction methods affect the representativeness of the reduced dataset, the energy consumption and the predictive performance of the model.
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.
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.