- idUS
- Investigación
- Ciencias
- Matemática Aplicada I
- Artículos (Matemática Aplicada I)
- Listar Artículos (Matemática Aplicada I) por autor
Listar Artículos (Matemática Aplicada I) por autor "Paluzo Hidalgo, Eduardo"
Mostrando ítems 1-14 de 14
-
Artículo
A Survey of Vectorization Methods in Topological Data Analysis
Ali, Dashti; Asaad, Aras; Jiménez Rodríguez, María José; Nanda, Vidit; Paluzo Hidalgo, Eduardo; Soriano Trigueros, Manuel (IEEE Computer Society, 2023-12)Attempts to incorporate topological information in supervised learning tasks have resulted in the creation of several ...
-
Artículo
Approximating lower-star persistence via 2D combinatorial map simplification
Damiand, Guillaume; Paluzo Hidalgo, Eduardo; Slechta, Ryan; González Díaz, Rocío (Elsevier, 2020)Filtration simplification consists of simplifying a given filtration while simultaneously controlling the perturbation in ...
-
Artículo
Emotion recognition in talking-face videos using persistent entropy and neural networks
Paluzo Hidalgo, Eduardo; González Díaz, Rocío; Aguirre Carrazana, Guilermo (American Institute of Mathematical Sciences (AIMS), 2022)The automatic recognition of a person’s emotional state has become a very active research field that involves scientists ...
-
Artículo
Neural-Network-Based Curve Fitting Using Totally Positive Rational Bases
González Díaz, Rocío; Mainardes, Emerson; Paluzo Hidalgo, Eduardo; Rubio Serrano, Beatriz (MDPI, 2020-12-10)This paper proposes a method for learning the process of curve fitting through a general class of totally positive rational ...
-
Artículo
Optimizing the Simplicial-Map Neural Network Architecture
Paluzo Hidalgo, Eduardo; González Díaz, Rocío; Gutiérrez Naranjo, Miguel Ángel; Heras, Jónathan (MDPI, 2021)Simplicial-map neural networks are a recent neural network architecture induced by simplicial maps defined between ...
-
Artículo
Representative datasets for neural networks
González Díaz, Rocío; Paluzo Hidalgo, Eduardo; Gutiérrez Naranjo, Miguel Ángel (Elsevier, 2018)Neural networks present big popularity and success in many fields. The large training time process problem is a very ...
-
Artículo
Representative Datasets: The Perceptron Case
González Díaz, Rocío; Gutiérrez Naranjo, Miguel Ángel; Paluzo Hidalgo, Eduardo (Cornell University, 2019)One of the main drawbacks of the practical use of neural networks is the long time needed in the training process. Such ...
-
Artículo
Simplicial-Map Neural Networks Robust to Adversarial Examples
Paluzo Hidalgo, Eduardo; González Díaz, Rocío; Gutiérrez Naranjo, Miguel Ángel; Heras, Jónathan (MDPI [Commercial Publisher], 2021-01-15)Broadly speaking, an adversarial example against a classification model occurs when a small perturbation on an input data ...
-
Artículo
Strong Euler well-composedness
Boutry, Nicolas; González Díaz, Rocío; Jiménez Rodríguez, María José; Paluzo Hidalgo, Eduardo (Springer, 2021)In this paper, we define a new flavour of well-composedness, called strong Euler well composedness. In the general setting ...
-
Artículo
Topology-based representative datasets to reduce neural network training resources
González Díaz, Rocío; Gutiérrez Naranjo, Miguel Ángel; Paluzo Hidalgo, Eduardo (Springer, 2022)One of the main drawbacks of the practical use of neural networks is the long time required in the training process. Such ...
-
Artículo
Towards a Philological Metric through a Topological Data Analysis Approach
Paluzo Hidalgo, Eduardo; González Díaz, Rocío; Gutiérrez Naranjo, Miguel Ángel (Cornell University, 2019)The canon of the baroque Spanish literature has been thoroughly studied with philological techniques. The major representatives ...
-
Artículo
Trainable and explainable simplicial map neural networks
Paluzo Hidalgo, Eduardo; González Díaz, Rocío; Gutiérrez Naranjo, Miguel Ángel (ELSEVIER SCIENCE INC, 2024)Simplicial map neural networks (SMNNs) are topology-based neural networks with interesting properties such as universal ...
-
Artículo
Two-hidden-layer feed-forward networks are universal approximators: A constructive approach
Paluzo Hidalgo, Eduardo; González Díaz, Rocío; Gutiérrez Naranjo, Miguel Ángel (ScienceDirect, 2020-11)It is well-known that artificial neural networks are universal approximators. The classical existence result proves that, ...
-
Artículo
Two-hidden-layer Feedforward Neural Networks are Universal Approximators: A Constructive Approach
González Díaz, Rocío; Gutiérrez Naranjo, Miguel Ángel; Paluzo Hidalgo, Eduardo (Cornell University, 2019)It is well known that Artificial Neural Networks are universal approximators. The classical result proves that, given a ...