Recurrent Neural Networks for Adaptive Feature Acquisition

Abstract : 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.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01874158
Contributor : Thierry Artieres <>
Submitted on : Friday, September 14, 2018 - 9:59:08 AM
Last modification on : Friday, July 5, 2019 - 3:26:03 PM
Long-term archiving on : Saturday, December 15, 2018 - 1:12:29 PM

File

contardo_RNN_adaptive_acquisit...
Files produced by the author(s)

Identifiers

Citation

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%2F978-3-319-46675-0_65⟩. ⟨hal-01874158⟩

Share

Metrics

Record views

102

Files downloads

232