Miguel Turullols, Laura de
Loading...
Email Address
person.page.identifierURI
Birth Date
Job Title
Last Name
Miguel Turullols
First Name
Laura de
person.page.departamento
Estadística, Informática y Matemáticas
person.page.instituteName
ISC. Institute of Smart Cities
ORCID
person.page.observainves
person.page.upna
Name
- Publications
- item.page.relationships.isAdvisorOfPublication
- item.page.relationships.isAdvisorTFEOfPublication
- item.page.relationships.isAuthorMDOfPublication
3 results
Search Results
Now showing 1 - 3 of 3
Publication Open Access Some properties of implications via aggregation functions and overlap functions(Taylor & Francis, 2014) Zapata, Hugo; Bustince Sola, Humberto; Miguel Turullols, Laura de; Guerra Errea, Carlos; Automática y Computación; Automatika eta Konputazioa; Universidad Pública de Navarra / Nafarroako Unibertsitate PublikoaIn this work, using the identification between implication operators and aggregation functions, we study the implication operators that are recovered from overlap functions. In particular, we focus in which properties of implication operators are preserved. We also study how negations can be defined in terms of overlap functions.Publication Embargo Non-symmetric over-time pooling using pseudo-grouping functions for convolutional neural networks(Elsevier, 2024) Ferrero Jaurrieta, Mikel; Paiva, Rui; Cruz, Anderson; Bedregal, Benjamin; Miguel Turullols, Laura de; Takáč, Zdenko; López Molina, Carlos; Bustince Sola, Humberto; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Institute of Smart Cities - ISCConvolutional Neural Networks (CNNs) are a family of networks that have become state-of-the-art in several fields of artificial intelligence due to their ability to extract spatial features. In the context of natural language processing, they can be used to build text classification models based on textual features between words. These networks fuse local features to generate global features in their over-time pooling layers. These layers have been traditionally built using the maximum function or other symmetric functions such as the arithmetic mean. It is important to note that the order of input local features is significant (i.e. the symmetry is not an inherent characteristic of the model). While this characteristic is appropriate for image-oriented CNNs, where symmetry might make the network robust to image rigid transformations, it seems counter-productive for text processing, where the order of the words is certainly important. Our proposal is, hence, to use non-symmetric pooling operators to replace the maximum or average functions. Specifically, we propose to perform over-time pooling using pseudo-grouping functions, a family of non-symmetric aggregation operators that generalize the maximum function. We present a construction method for pseudo-grouping functions and apply different examples of this family to over-time pooling layers in text-oriented CNNs. Our proposal is tested on seven different models and six different datasets in the context of engineering applications, e.g. text classification. The results show an overall improvement of the models when using non-symmetric pseudo-grouping functions over the traditional pooling function.Publication Open Access Description and properties of curve-based monotone functions(Springer, 2019) Sesma Sara, Mikel; Miguel Turullols, Laura de; Roldán López de Hierro, Antonio Francisco; Špirková, Jana; Mesiar, Radko; Bustince Sola, Humberto; Institute of Smart Cities - ISCCurve-based monotonicity is one of the lately introduced relaxations of monotonicity. As directional monotonicity regards monotonicity along fixed rays, which are given by real vectors, curve-based monotonicity studies the increase of functions with respect to a general curve. In this work we study some theoretical properties of this type of monotonicity and we relate this concept with previous relaxations of monotonicity.