no code implementations • 18 Sep 2020 • Marc Ortiz, Florian Scheidegger, Marc Casas, Cristiano Malossi, Eduard Ayguadé
In this work, we leverage ensemble learning as a tool for the creation of faster, smaller, and more accurate deep learning models.
1 code implementation • 27 Jul 2020 • Ferran Parés, Anna Arias-Duart, Dario Garcia-Gasulla, Gema Campo-Francés, Nina Viladrich, Eduard Ayguadé, Jesús Labarta
In this work we introduce the MAMe dataset, an image classification dataset with remarkable high resolution and variable shape properties.
Ranked #1 on Image Classification on MAMe
no code implementations • 26 Nov 2019 • Raquel Pérez-Arnal, Dario Garcia-Gasulla, David Torrents, Ferran Parés, Ulises Cortés, Jesús Labarta, Eduard Ayguadé
Finding tumour genetic markers is essential to biomedicine due to their relevance for cancer detection and therapy development.
1 code implementation • 20 Nov 2019 • Ferran Parés, Dario Garcia-Gasulla, Harald Servat, Jesús Labarta, Eduard Ayguadé
In sight of the increasing importance of problems that can benefit from exploiting high-resolution (HR) and variable-shape, and with the goal of promoting research in that direction, we introduce a new family of datasets (MetH).
no code implementations • 8 Nov 2019 • Victor Gimenez-Abalos, Armand Vilalta, Dario Garcia-Gasulla, Jesus Labarta, Eduard Ayguadé
The purpose of feature extraction on convolutional neural networks is to reuse deep representations learnt for a pre-trained model to solve a new, potentially unrelated problem.
1 code implementation • 14 May 2019 • Diego Marrón, Eduard Ayguadé, José Ramon Herrero, Albert Bifet
This paper presents Elastic Swap Random Forest ({\em ESRF}), a method for reducing the number of trees in the ARF ensemble while providing similar accuracy.
no code implementations • 24 Apr 2018 • Raquel Pérez-Arnal, Armand Vilalta, Dario Garcia-Gasulla, Ulises Cortés, Eduard Ayguadé, Jesus Labarta
WordNet, which includes a wide variety of concepts associated with words (i. e., synsets), is often used as a source for computing those distances.
no code implementations • 14 Apr 2018 • Marc Ortiz, Adrián Cristal, Eduard Ayguadé, Marc Casas
The use of low-precision fixed-point arithmetic along with stochastic rounding has been proposed as a promising alternative to the commonly used 32-bit floating point arithmetic to enhance training neural networks training in terms of performance and energy efficiency.
no code implementations • WS 2017 • Dario Garcia-Gasulla, Armand Vilalta, Ferran Parés, Jonatan Moreno, Eduard Ayguadé, Jesus Labarta, Ulises Cortés, Toyotaro Suzumura
Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes.
no code implementations • WS 2017 • Armand Vilalta, Dario Garcia-Gasulla, Ferran Parés, Eduard Ayguadé, Jesus Labarta, Ulises Cortés, Toyotaro Suzumura
In this paper we evaluate the impact of using the Full-Network embedding in this setting, replacing the original image representation in a competitive multimodal embedding generation scheme.
no code implementations • ICLR 2018 • Dario Garcia-Gasulla, Armand Vilalta, Ferran Parés, Jonatan Moreno, Eduard Ayguadé, Jesus Labarta, Ulises Cortés, Toyotaro Suzumura
Transfer learning for feature extraction can be used to exploit deep representations in contexts where there is very few training data, where there are limited computational resources, or when tuning the hyper-parameters needed for training is not an option.
2 code implementations • 27 Mar 2017 • Ferran Parés, Dario Garcia-Gasulla, Armand Vilalta, Jonatan Moreno, Eduard Ayguadé, Jesús Labarta, Ulises Cortés, Toyotaro Suzumura
We introduce a community detection algorithm (Fluid Communities) based on the idea of fluids interacting in an environment, expanding and contracting as a result of that interaction.
Data Structures and Algorithms Social and Information Networks Physics and Society
no code implementations • 3 Mar 2017 • Dario Garcia-Gasulla, Ferran Parés, Armand Vilalta, Jonatan Moreno, Eduard Ayguadé, Jesús Labarta, Ulises Cortés, Toyotaro Suzumura
We seek to provide new insights into the behavior of CNN features, particularly the ones from convolutional layers, as this can be relevant for their application to knowledge representation and reasoning.
no code implementations • 2 Nov 2016 • Dario Garcia-Gasulla, Eduard Ayguadé, Jesús Labarta, Ulises Cortés
Link prediction, the problem of identifying missing links among a set of inter-related data entities, is a popular field of research due to its application to graph-like domains.