no code implementations • 3 Apr 2024 • Iván Sevillano-García, Julián Luengo, Francisco Herrera
As Artificial Intelligence systems become integral across domains, the demand for explainability grows.
no code implementations • 20 Feb 2023 • Adrian Peláez-Vegas, Pablo Mesejo, Julián Luengo
Semantic segmentation is one of the most challenging tasks in computer vision.
2 code implementations • 7 Jun 2022 • Ignacio Aguilera-Martos, Ángel M. García-Vico, Julián Luengo, Sergio Damas, Francisco J. Melero, José Javier Valle-Alonso, Francisco Herrera
The combination of convolutional and recurrent neural networks is a promising framework that allows the extraction of high-quality spatio-temporal features together with its temporal dependencies, which is key for time series prediction problems such as forecasting, classification or anomaly detection, amongst others.
1 code implementation • 8 Sep 2021 • Anabel Gómez-Ríos, Julián Luengo, Francisco Herrera
This algorithm filters and relabels instances of the training set based on the predictions and their probabilities made by the backbone neural network during the training process.
no code implementations • 26 May 2021 • Jacinto Carrasco, Irina Markova, David López, Ignacio Aguilera, Diego García, Marta García-Barzana, Manuel Arias-Rodil, Julián Luengo, Francisco Herrera
The research in anomaly detection lacks a unified definition of what represents an anomalous instance.
no code implementations • 21 Oct 2018 • José-Ramón Cano, Julián Luengo, Salvador García
Changing the class labels of the data set (relabelling) is useful for this.
no code implementations • 27 Mar 2018 • Anabel Gómez-Ríos, Siham Tabik, Julián Luengo, ASM Shihavuddin, Bartosz Krawczyk, Francisco Herrera
The recognition of coral species based on underwater texture images pose a significant difficulty for machine learning algorithms, due to the three following challenges embedded in the nature of this data: 1) datasets do not include information about the global structure of the coral; 2) several species of coral have very similar characteristics; and 3) defining the spatial borders between classes is difficult as many corals tend to appear together in groups.
no code implementations • 6 Apr 2017 • Diego García-Gil, Julián Luengo, Salvador García, Francisco Herrera
In any knowledge discovery process the value of extracted knowledge is directly related to the quality of the data used.