Recurrent Neural Networks for Adaptive Feature Acquisition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Recurrent Neural Networks for Adaptive Feature Acquisition

Résumé

We propose to tackle the cost-sensitive learning problem, where each feature is associated to a particular acquisition cost. We propose a new model with the following key properties: (i) it acquires features in an adaptive way, (ii) features can be acquired per block (several at a time) so that this model can deal with high dimensional data, and (iii) it relies on representation-learning ideas. The effectiveness of this approach is demonstrated on several experiments considering a variety of datasets and with different cost settings.
Fichier principal
Vignette du fichier
contardo_RNN_adaptive_acquisition_ICONIP2016.pdf (294.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01874158 , version 1 (14-09-2018)

Identifiants

Citer

Thierry Artières, Gabriella Contardo, Ludovic Denoyer. Recurrent Neural Networks for Adaptive Feature Acquisition. 23rd International Conference on Neural Information Processing (ICONIP 2016), Oct 2016, Kyoto, Japan. pp.591-599, ⟨10.1007/978-3-319-46675-0_65⟩. ⟨hal-01874158⟩
135 Consultations
428 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More