activity
20102013
most citedDisentangling Factors of Variation via Generative Entangling

76 citations · 211 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG201319 cited

Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines

Guillaume Desjardins, Razvan Pascanu, Aaron Courville +1

This paper introduces the Metric-Free Natural Gradient (MFNG) algorithm for training Boltzmann Machines. Similar in spirit to the Hessian-Free method of Martens [8], our algorithm…

stat.ML201224 cited

Joint Training of Deep Boltzmann Machines

Ian Goodfellow, Aaron Courville, Yoshua Bengio

We introduce a new method for training deep Boltzmann machines jointly. Prior methods require an initial learning pass that trains the deep Boltzmann machine greedily, one layer at…

cs.LG201214 cited

Texture Modeling with Convolutional Spike-and-Slab RBMs and Deep Extensions

Heng Luo, Pierre Luc Carrier, Aaron Courville +1

We apply the spike-and-slab Restricted Boltzmann Machine (ssRBM) to texture modeling. The ssRBM with tiled-convolution weight sharing (TssRBM) achieves or surpasses the state-of-th…

stat.ML201276 cited

Disentangling Factors of Variation via Generative Entangling

Guillaume Desjardins, Aaron Courville, Yoshua Bengio

Here we propose a novel model family with the objective of learning to disentangle the factors of variation in data. Our approach is based on the spike-and-slab restricted Boltzman…

cs.LG201249 cited

Large-Scale Feature Learning With Spike-and-Slab Sparse Coding

Ian Goodfellow, Aaron Courville, Yoshua Bengio

We consider the problem of object recognition with a large number of classes. In order to overcome the low amount of labeled examples available in this setting, we introduce a new…

stat.ML201029 cited

Adaptive Parallel Tempering for Stochastic Maximum Likelihood Learning of RBMs

Guillaume Desjardins, Aaron Courville, Yoshua Bengio

Restricted Boltzmann Machines (RBM) have attracted a lot of attention of late, as one the principle building blocks of deep networks. Training RBMs remains problematic however, bec…