Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Eduardo Paluzo-Hidalgo"'
Autor:
Matteo Rucco, Javier Perera-Lago, Eduardo Paluzo-Hidalgo, Victor Toscano-Duran, Miguel A. Gutiérrez-Naranjo, Rocio Gonzalez-Diaz
Publikováno v:
Open Research Europe, Vol 4 (2024)
In recent years, deep learning has gained popularity for its ability to solve complex classification tasks. It provides increasingly better results thanks to the development of more accurate models, the availability of huge volumes of data and the im
Externí odkaz:
https://doaj.org/article/f4f9346ede664b448d5ec20b6aabbb83
Publikováno v:
Electronic Research Archive, Vol 30, Iss 2, Pp 644-660 (2022)
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. Our main objective
Externí odkaz:
https://doaj.org/article/6dda8408131147dea2a839229f9b766e
Publikováno v:
Journal of Imaging, Vol 7, Iss 9, p 173 (2021)
Simplicial-map neural networks are a recent neural network architecture induced by simplicial maps defined between simplicial complexes. It has been proved that simplicial-map neural networks are universal approximators and that they can be refined t
Externí odkaz:
https://doaj.org/article/6f749f66c6744304adb822d630d59da9
Publikováno v:
Mathematics, Vol 9, Iss 2, p 169 (2021)
Broadly speaking, an adversarial example against a classification model occurs when a small perturbation on an input data point produces a change on the output label assigned by the model. Such adversarial examples represent a weakness for the safety
Externí odkaz:
https://doaj.org/article/092c9012175e4e78938be4e47fa18261
Publikováno v:
Mathematics, Vol 8, Iss 12, p 2197 (2020)
This paper proposes a method for learning the process of curve fitting through a general class of totally positive rational bases. The approximation is achieved by finding suitable weights and control points to fit the given set of data points using
Externí odkaz:
https://doaj.org/article/7e6a155449b64f4da99ce8357c72c045
Publikováno v:
Neural Computing and Applications. 34:14397-14413
One of the main drawbacks of the practical use of neural networks is the long time required in the training process. Such a training process consists of an iterative change of parameters trying to minimize a loss function. These changes are driven by
Publikováno v:
Journal of Imaging
Journal of Imaging, Vol 7, Iss 173, p 173 (2021)
RIUR. Repositorio Institucional de la Universidad de La Rioja
instname
idUS. Depósito de Investigación de la Universidad de Sevilla
Volume 7
Issue 9
Journal of Imaging, Vol 7, Iss 173, p 173 (2021)
RIUR. Repositorio Institucional de la Universidad de La Rioja
instname
idUS. Depósito de Investigación de la Universidad de Sevilla
Volume 7
Issue 9
Simplicial-map neural networks are a recent neural network architecture induced by simplicial maps defined between simplicial complexes. It has been proved that simplicial-map neural networks are universal approximators and that they can be refined t
Publikováno v:
idUS: Depósito de Investigación de la Universidad de Sevilla
Universidad de Sevilla (US)
Mathematics, Vol 8, Iss 2197, p 2197 (2020)
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Consejo Superior de Investigaciones Científicas (CSIC)
Zaguán: Repositorio Digital de la Universidad de Zaragoza
Universidad de Zaragoza
Mathematics
Volume 8
Issue 12
idUS. Depósito de Investigación de la Universidad de Sevilla
instname
Universidad de Sevilla (US)
Mathematics, Vol 8, Iss 2197, p 2197 (2020)
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Consejo Superior de Investigaciones Científicas (CSIC)
Zaguán: Repositorio Digital de la Universidad de Zaragoza
Universidad de Zaragoza
Mathematics
Volume 8
Issue 12
idUS. Depósito de Investigación de la Universidad de Sevilla
instname
This paper proposes a method for learning the process of curve fitting through a general class of totally positive rational bases. The approximation is achieved by finding suitable weights and control points to fit the given set of data points using
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::442705c6d41aa3bbaa7fe736331f8f9a
Publikováno v:
idUS. Depósito de Investigación de la Universidad de Sevilla
instname
Pattern Recognition Letters
Pattern Recognition Letters, Elsevier, 2020, 131, pp.314-321. ⟨10.1016/j.patrec.2020.01.018⟩
instname
Pattern Recognition Letters
Pattern Recognition Letters, Elsevier, 2020, 131, pp.314-321. ⟨10.1016/j.patrec.2020.01.018⟩
International audience; Filtration simplification consists of simplifying a given filtration while simultaneously controlling the perturbation in the associated persistence diagrams. In this paper, we propose a filtration simplification algorithm for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::021c39bec60b02eb028a3ef418ad86b8
Publikováno v:
idUS: Depósito de Investigación de la Universidad de Sevilla
Universidad de Sevilla (US)
idUS. Depósito de Investigación de la Universidad de Sevilla
instname
Universidad de Sevilla (US)
idUS. Depósito de Investigación de la Universidad de Sevilla
instname
It is well known that Artificial Neural Networks are universal approximators. The classical result proves that, given a continuous function on a compact set on an n-dimensional space, then there exists a one-hidden-layer feedforward network which app
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0176d097b932a31510f63986d2cdae26