Sokolovska N. auteur aut IRD Nguyen Thanh Hai auteur aut IRD Clément K. auteur aut IRD Zucker Jean-Daniel auteur aut IRD text bookSection eng text/pdf born digital access Feature selection is used to preserve significant properties of data in a compact space. In particular, feature selection is needed in applications, where information comes from multiple heterogeneous high dimensional sources. Data integration, however, is a challenge in itself. In our contribution, we introduce a feature selection framework based on powerful visualisation capabilities of self-organising maps, where the deep structure can be learned in a supervised or unsupervised manner. For a supervised version of the deep SOM, we propose to carry out inference with a linear SVM. A forward-backward procedure helps to converge to an optimal feature set. We show by experiments on real large-scale biomedical data set that the proposed methods embed data in a new compact meaningful representation, allow to visualise biomedical signatures, and also lead to a reasonable classification accuracy compared to the state-of-the-art methods. specialized 122 050 020 084 5079-5086 Piscataway IEEE 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver (CAN), 2016/07/24-29 https://www.documentation.ird.fr/hor/fdi:010069089 10.1109/IJCNN.2016.7727869 978-1-5090-0619-9 [F B010069089] https://www.documentation.ird.fr/hor/fdi:010069089 https://www.documentation.ird.fr/intranet/publi/depot/2017-02-01/010069089.pdf Accès réservé (Intranet de l'IRD) IRD - Base Horizon / Pleins textes 2017-02-01 2023-02-22 fdi:010069089 fre