A Spike and Slab Restricted Boltzmann Machine

Aaron Courville, James Bergstra, Yoshua Bengio
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, PMLR 15:233-241, 2011.

Abstract

We introduce the spike and slab Restricted Boltzmann Machine, characterized by having both a real-valued vector, the slab, and a binary variable, the spike, associated with each unit in the hidden layer. The model possesses some practical properties such as being amenable to Block Gibbs sampling as well as being capable of generating similar latent representations of the data to the recently introduced mean and covariance Restricted Boltzmann Machine. We illustrate how the spike and slab Restricted Boltzmann Machine achieves competitive performance on the CIFAR-10 object recognition task.

Cite this Paper

BibTeX
@InProceedings{pmlr-v15-courville11a, title = {A Spike and Slab Restricted Boltzmann Machine}, author = {Courville, Aaron and Bergstra, James and Bengio, Yoshua}, booktitle = {Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics}, pages = {233--241}, year = {2011}, editor = {Gordon, Geoffrey and Dunson, David and Dudík, Miroslav}, volume = {15}, series = {Proceedings of Machine Learning Research}, address = {Fort Lauderdale, FL, USA}, month = {11--13 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v15/courville11a/courville11a.pdf}, url = {https://proceedings.mlr.press/v15/courville11a.html}, abstract = {We introduce the spike and slab Restricted Boltzmann Machine, characterized by having both a real-valued vector, the slab, and a binary variable, the spike, associated with each unit in the hidden layer. The model possesses some practical properties such as being amenable to Block Gibbs sampling as well as being capable of generating similar latent representations of the data to the recently introduced mean and covariance Restricted Boltzmann Machine. We illustrate how the spike and slab Restricted Boltzmann Machine achieves competitive performance on the CIFAR-10 object recognition task.} }
Endnote
%0 Conference Paper %T A Spike and Slab Restricted Boltzmann Machine %A Aaron Courville %A James Bergstra %A Yoshua Bengio %B Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2011 %E Geoffrey Gordon %E David Dunson %E Miroslav Dudík %F pmlr-v15-courville11a %I PMLR %P 233--241 %U https://proceedings.mlr.press/v15/courville11a.html %V 15 %X We introduce the spike and slab Restricted Boltzmann Machine, characterized by having both a real-valued vector, the slab, and a binary variable, the spike, associated with each unit in the hidden layer. The model possesses some practical properties such as being amenable to Block Gibbs sampling as well as being capable of generating similar latent representations of the data to the recently introduced mean and covariance Restricted Boltzmann Machine. We illustrate how the spike and slab Restricted Boltzmann Machine achieves competitive performance on the CIFAR-10 object recognition task.
RIS
TY - CPAPER TI - A Spike and Slab Restricted Boltzmann Machine AU - Aaron Courville AU - James Bergstra AU - Yoshua Bengio BT - Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics DA - 2011/06/14 ED - Geoffrey Gordon ED - David Dunson ED - Miroslav Dudík ID - pmlr-v15-courville11a PB - PMLR DP - Proceedings of Machine Learning Research VL - 15 SP - 233 EP - 241 L1 - http://proceedings.mlr.press/v15/courville11a/courville11a.pdf UR - https://proceedings.mlr.press/v15/courville11a.html AB - We introduce the spike and slab Restricted Boltzmann Machine, characterized by having both a real-valued vector, the slab, and a binary variable, the spike, associated with each unit in the hidden layer. The model possesses some practical properties such as being amenable to Block Gibbs sampling as well as being capable of generating similar latent representations of the data to the recently introduced mean and covariance Restricted Boltzmann Machine. We illustrate how the spike and slab Restricted Boltzmann Machine achieves competitive performance on the CIFAR-10 object recognition task. ER -
APA
Courville, A., Bergstra, J. & Bengio, Y.. (2011). A Spike and Slab Restricted Boltzmann Machine. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 15:233-241 Available from https://proceedings.mlr.press/v15/courville11a.html.

Related Material