Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Pares, Ferran"'
AI explainability improves the transparency of models, making them more trustworthy. Such goals are motivated by the emergence of deep learning models, which are obscure by nature; even in the domain of images, where deep learning has succeeded the m
Externí odkaz:
http://arxiv.org/abs/2109.15035
Autor:
Parés, Ferran, Arias-Duart, Anna, Garcia-Gasulla, Dario, Campo-Francés, Gema, Viladrich, Nina, Ayguadé, Eduard, Labarta, Jesús
In the image classification task, the most common approach is to resize all images in a dataset to a unique shape, while reducing their precision to a size which facilitates experimentation at scale. This practice has benefits from a computational pe
Externí odkaz:
http://arxiv.org/abs/2007.13693
Autor:
Pérez-Arnal, Raquel, Garcia-Gasulla, Dario, Torrents, David, Parés, Ferran, Cortés, Ulises, Labarta, Jesús, Ayguadé, Eduard
Finding tumour genetic markers is essential to biomedicine due to their relevance for cancer detection and therapy development. In this paper, we explore a recently released dataset of chromosome rearrangements in 2,586 cancer patients, where differe
Externí odkaz:
http://arxiv.org/abs/1911.11471
High-resolution and variable-shape images have not yet been properly addressed by the AI community. The approach of down-sampling data often used with convolutional neural networks is sub-optimal for many tasks, and has too many drawbacks to be consi
Externí odkaz:
http://arxiv.org/abs/1911.08953
Autor:
Vilalta, Armand, Garcia-Gasulla, Dario, Parés, Ferran, Ayguadé, Eduard, Labarta, Jesus, Cortés, Ulises, Suzumura, Toyotaro
The current state-of-the-art for image annotation and image retrieval tasks is obtained through deep neural networks, which combine an image representation and a text representation into a shared embedding space. In this paper we evaluate the impact
Externí odkaz:
http://arxiv.org/abs/1707.09872
Autor:
Garcia-Gasulla, Dario, Vilalta, Armand, Parés, Ferran, Moreno, Jonatan, Ayguadé, Eduard, Labarta, Jesus, Cortés, Ulises, Suzumura, Toyotaro
Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network representations are implemented within vector embedding spaces, which enabl
Externí odkaz:
http://arxiv.org/abs/1707.07465
Autor:
Garcia-Gasulla, Dario, Vilalta, Armand, Parés, Ferran, Moreno, Jonatan, Ayguadé, Eduard, Labarta, Jesus, Cortés, Ulises, Suzumura, Toyotaro
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
Externí odkaz:
http://arxiv.org/abs/1705.07706
Autor:
Parés, Ferran, Garcia-Gasulla, Dario, Vilalta, Armand, Moreno, Jonatan, Ayguadé, Eduard, Labarta, Jesús, Cortés, Ulises, Suzumura, Toyotaro
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. Fluid Communities is based on the propagation methodology, which re
Externí odkaz:
http://arxiv.org/abs/1703.09307
Autor:
Garcia-Gasulla, Dario, Parés, Ferran, Vilalta, Armand, Moreno, Jonatan, Ayguadé, Eduard, Labarta, Jesús, Cortés, Ulises, Suzumura, Toyotaro
Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within a trained
Externí odkaz:
http://arxiv.org/abs/1703.01127
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.