Visualizing Data using t-SNE
http://www.jmlr.org/papers/volume9/vandermaaten08a/vandermaaten08a.pdf
Reducing the Dimensionality of Data with Neural Networks
https://www.cs.toronto.edu/~hinton/science.pdf
A fast learning algorithm for deep belief nets
https://www.cs.toronto.edu/~hinton/absps/fastnc.pdf
Why Does Unsupervised Pre-training Help Deep Learning?
http://www.jmlr.org/papers/volume11/erhan10a/erhan10a.pdf
A Better Way to Pretrain Deep Boltzmann Machines
http://www.cs.toronto.edu/~hinton/absps/DBM_pretrain.pdf
On Deep Generative Models with Applications to Recognition
http://www.cs.toronto.edu/~hinton/absps/ranzato_cvpr2011.pdf
LEARNING A BETTER REPRESENTATION OF SPEECH SOUND WAVES USING RESTRICTED BOLTZMANN MACHINES
http://www.cs.toronto.edu/~hinton/absps/jaitly_ICASSP2011.pdf
Rectified Linear Units Improve Restricted Boltzmann Machines
http://www.cs.toronto.edu/~hinton/absps/reluICML.pdf
Generative versus discriminative training of RBMs for classification of fMRI images
http://www.cs.toronto.edu/~hinton/absps/fmrinips.pdf
Restricted Boltzmann Machines for Collaborative Filtering
http://www.cs.toronto.edu/~hinton/absps/netflix.pdf
On Contrastive Divergence Learning
http://www.cs.toronto.edu/~hinton/absps/cdmiguel.pdf