6 papers
Semi-Supervised Machine Learning: a Homological Approach
Adrián Inés, César Domínguez, Jónathan Heras +2
In this paper we describe the mathematical foundations of a new approach to semi-supervised Machine Learning. Using techniques of Symbolic Computation and Computer Algebra, we appl…
Coupling of Magnetic Phases at Nickelate Interfaces
C. Domínguez, J. Fowlie, A. B. Georgescu +9
In this work we present a model system built out of artificially layered materials, allowing us to understand the interrelation of magnetic phases with that of the metallic-insulat…
Semi-Supervised Learning for Image Classification using Compact Networks in the BioMedical Context
Adrián Inés, Andrés Díaz-Pinto, César Domínguez +3
The development of mobile and on the edge applications that embed deep convolutional neural models has the potential to revolutionise biomedicine. However, most deep learning model…
A Topological Approach for Semi-Supervised Learning
Adrián Inés, César Domínguez, Jónathan Heras +2
Nowadays, Machine Learning and Deep Learning methods have become the state-of-the-art approach to solve data classification tasks. In order to use those methods, it is necessary to…
Text Classification Models for Form Entity Linking
María Villota, César Domínguez, Jónathan Heras +2
Forms are a widespread type of template-based document used in a great variety of fields including, among others, administration, medicine, finance, or insurance. The automatic ext…
Neural Style Transfer and Unpaired Image-to-Image Translation to deal with the Domain Shift Problem on Spheroid Segmentation
Manuel García-Domínguez, César Domínguez, Jónathan Heras +2
Background and objectives. Domain shift is a generalisation problem of machine learning models that occurs when the data distribution of the training set is different to the data d…