Deep Self-Organising Maps for efficient heterogeneous biomedical signatures extraction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Deep Self-Organising Maps for efficient heterogeneous biomedical signatures extraction

Résumé

—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.
Fichier principal
Vignette du fichier
2016 07 DeepSOMSVM.pdf (4.47 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01783577 , version 1 (02-05-2018)

Identifiants

Citer

Nataliya Sokolovska, Nguyen Thanh Hai, Karine Clément, Jean-Daniel Zucker. Deep Self-Organising Maps for efficient heterogeneous biomedical signatures extraction. 2016 International Joint Conference on Neural Networks (IJCNN), Jul 2016, Vancouver, Canada. ⟨10.1109/IJCNN.2016.7727869⟩. ⟨hal-01783577⟩
30 Consultations
99 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More