Classification of Sets using Restricted Boltzmann Machines

Jérôme Louradour, Hugo Larochelle
Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, PMLR R9:520-536, 2011.

Abstract

We consider the problem of classification when inputs correspond to sets of vectors. This setting occurs in many problems such as the classification of pieces of mail containing several pages, of web sites with several sections or of images that have been pre-segmented into smaller regions. We propose generalizations of the restricted Boltzmann machine (RBM) that are appropriate in this context and explore how to incorporate different assumptions about the relationship between the input sets and the target class within the RBM. In experiments on standard multiple-instance learning datasets, we demonstrate the competitiveness of approaches based on RBMs and apply the proposed variants to the problem of incoming mail classification.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR9-louradour11a, title = {Classification of Sets using Restricted {B}oltzmann Machines}, author = {Louradour, J{\'e}r{\^o}me and Larochelle, Hugo}, booktitle = {Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence}, pages = {520--536}, year = {2011}, editor = {Cozman, Fabio and Pfeffer, Avi}, volume = {R9}, series = {Proceedings of Machine Learning Research}, month = {14--17 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r9/main/assets/louradour11a/louradour11a.pdf}, url = {https://proceedings.mlr.press/r9/louradour11a.html}, abstract = {We consider the problem of classification when inputs correspond to sets of vectors. This setting occurs in many problems such as the classification of pieces of mail containing several pages, of web sites with several sections or of images that have been pre-segmented into smaller regions. We propose generalizations of the restricted Boltzmann machine (RBM) that are appropriate in this context and explore how to incorporate different assumptions about the relationship between the input sets and the target class within the RBM. In experiments on standard multiple-instance learning datasets, we demonstrate the competitiveness of approaches based on RBMs and apply the proposed variants to the problem of incoming mail classification.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Classification of Sets using Restricted Boltzmann Machines %A Jérôme Louradour %A Hugo Larochelle %B Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2011 %E Fabio Cozman %E Avi Pfeffer %F pmlr-vR9-louradour11a %I PMLR %P 520--536 %U https://proceedings.mlr.press/r9/louradour11a.html %V R9 %X We consider the problem of classification when inputs correspond to sets of vectors. This setting occurs in many problems such as the classification of pieces of mail containing several pages, of web sites with several sections or of images that have been pre-segmented into smaller regions. We propose generalizations of the restricted Boltzmann machine (RBM) that are appropriate in this context and explore how to incorporate different assumptions about the relationship between the input sets and the target class within the RBM. In experiments on standard multiple-instance learning datasets, we demonstrate the competitiveness of approaches based on RBMs and apply the proposed variants to the problem of incoming mail classification. %Z Reissued by PMLR on 04 October 2026.
APA
Louradour, J. & Larochelle, H.. (2011). Classification of Sets using Restricted Boltzmann Machines. Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R9:520-536 Available from https://proceedings.mlr.press/r9/louradour11a.html. Reissued by PMLR on 04 October 2026.

Related Material