Fetching the paper…
Reading the bibliography…
Generative Stochastic Networks (GSNs) have been recently introduced as an alternative to traditional probabilistic modeling: instead of parametrizing the data distribution directly, one parametrizes a transition operator for a Markov chain whose stationary distribution is an estimator of the data generating distribution.
A learning algorithm for Boltzmann machines
Ackley, D. H., Hinton, G. E., and Sejnowski, T. J. (1985) · 1985
Earlier work this paper cites.
Modeling high-dimensional discrete data with multi-layer neural networks
Bengio, Y. and Bengio, S. (2000) · 2000
Earlier work this paper cites.
Algorithms for manifold learning
Cayton, L. (2005) · 2005
Earlier work this paper cites.
Modeling human motion using binary latent variables
Taylor, G., Hinton, G. E., and Roweis, S. (2007) · 2007
Earlier work this paper cites.
Zero-data learning of new tasks
Larochelle, H., Erhan, D., and Bengio, Y. (2008) · 2008
Earlier work this paper cites.
Extracting and composing robust features with denoising autoencoders
Vincent, P., Larochelle, H., Bengio, Y., and Manzagol, P.-A. (2008) · 2008
Earlier work this paper cites.
Deep learning via semi-supervised embedding
Weston, J., Ratle, F., and Collobert, R. (2008) · 2008
Earlier work this paper cites.
Learning deep architectures for AI
Bengio, Y. (2009) · 2009
Earlier work this paper cites.
Deep Boltzmann machines
Salakhutdinov, R. and Hinton, G. (2009) · 2009
Earlier work this paper cites.
Factored conditional restricted Boltzmann machines for modeling motion style
Taylor, G. and Hinton, G. (2009) · 2009
Cited alongside, same era.
Theano: a CPU and GPU math expression compiler
Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., and Bengio, Y. (2010) · 2010
Cited alongside, same era.
Why does unsupervised pre-training help deep learning?
Erhan, D., Bengio, Y., Courville, A., Manzagol, P.-A., Vincent, P., and Bengio, S. (2010) · 2010
Cited alongside, same era.
Sample complexity of testing the manifold hypothesis
Narayanan, H. and Mitter, S. (2010) · 2010
Cited alongside, same era.
Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., and Manzagol, P.-A. (2010) · 2010
Cited alongside, same era.
Deep learning of representations for unsupervised and transfer learning
Theano: new features and speed improvements
Bastien, F., Lamblin, P., Pascanu, R., Bergstra, J., Goodfellow, I. J., Bergeron, A., Bouchard, N., and Bengio, Y. (2012) · 2012
Later among the works it cites.
Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription
Boulanger-Lewandowski, N., Bengio, Y., and Vincent, P. (2012) · 2012
Later among the works it cites.
Machine Learning: a Probabilistic Perspective
Murphy, K. P. (2012) · 2012
Later among the works it cites.
What regularized auto-encoders learn from the data generating distribution
Alain, G. and Bengio, Y. (2013) · 2013
Closest in time.
Generalized denoising auto-encoders as generative models
Bengio, Y., Yao, L., Alain, G., and Vincent, P. (2013d) · 2013
Closest in time.
Rnade: The real-valued neural autoregressive density-estimator
Benigno, U., Iain, M., and Hugo, L. (2013) · 2013
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Bengio, Y. (2011) · 2011
Cited alongside, same era.
Spike-and-slab sparse coding for unsupervised feature discovery
Goodfellow, I. J., Courville, A., and Bengio, Y. (2011) · 2011
Cited alongside, same era.
The Neural Autoregressive Distribution Estimator
Larochelle, H. and Murray, I. (2011) · 2011
Cited alongside, same era.
Unsupervised and transfer learning challenge: a deep learning approach
Mesnil, G., Dauphin, Y., Glorot, X., Rifai, S., Bengio, Y., Goodfellow, I., Lavoie, E., Muller, X., Desjardins, G., Warde-Farley, D., Vincent, P., Courville, A., and Bergstra, J. (2011) · 2011
Cited alongside, same era.
Advances in neural information processing systems 26 (nips’13)
(-1)
Cited in the paper.
Better mixing via deep representations
Bengio, Y., Mesnil, G., Dauphin, Y., and Rifai, S. (2013a)
Cited in the paper.
Bounding the test log-likelihood of generative models
Bengio, Y., Yao, L., and Cho, K. (2013b)
Cited in the paper.
Closest in time.
A deep and tractable density estimator
Benigno Uria, Iain Murray, H. L. (2013) · 2013
Closest in time.
Knowledge matters: Importance of prior information for optimization
Gulcehre, C. and Bengio, Y. (2013) · 2013
Closest in time.
One-shot learning by inverting a compositional causal process
Lake, B., Salakhutdinov, R., and Tenenbaum, J. (2013) · 2013
Closest in time.