UFLDL Recommended Readings
From Ufldl
Line 5: | Line 5: | ||
* Natural Image Statistics book, Hyvarinen et al. | * Natural Image Statistics book, Hyvarinen et al. | ||
* Olshausen and Field Sparse Coding paper (1996) | * Olshausen and Field Sparse Coding paper (1996) | ||
- | * Learning Deep Architectures for AI. (Broad landscape description of the field, but technical details there are hard to follow so ignore that.) | + | * [http://www.iro.umontreal.ca/~bengioy/papers/ftml_book.pdf] Yoshua Bengio. Learning Deep Architectures for AI. FTML 2009. (Broad landscape description of the field, but technical details there are hard to follow so ignore that.) |
- | * Rajat Raina | + | * [http://www.cs.stanford.edu/~ang/papers/icml07-selftaughtlearning.pdf] Rajat Raina, Alexis Battle, Honglak Lee, Benjamin Packer and Andrew Y. Ng. Self-taught learning: Transfer learning from unlabeled data. ICML 2007 |
Autoencoders: | Autoencoders: | ||
- | * Greedy | + | * [http://www-etud.iro.umontreal.ca/~larocheh/publications/greedy-deep-nets-nips-06.pdf] Bengio, Y., Lamblin, P., Popovici, P., Larochelle, H. Greedy Layer-Wise Training of Deep Networks. NIPS 2006 |
- | * Dumitru Erhan, Yoshua Bengio, Aaron Courville, Pierre-Antoine Manzagol, Pascal Vincent, and Samy Bengio. Why Does Unsupervised Pre-training Help Deep Learning? | + | * [http://www.jmlr.org/papers/volume11/erhan10a/erhan10a.pdf] Dumitru Erhan, Yoshua Bengio, Aaron Courville, Pierre-Antoine Manzagol, Pascal Vincent, and Samy Bengio. Why Does Unsupervised Pre-training Help Deep Learning? JMLR 2010 |
* Larochelle, Erhan, Courville, Bergstra, BBengio, 2007. (Someone read this and let us know if this is worth keeping,.) | * Larochelle, Erhan, Courville, Bergstra, BBengio, 2007. (Someone read this and let us know if this is worth keeping,.) | ||
* [http://www.cs.toronto.edu/~hinton/science.pdf] [http://www.cs.toronto.edu/~hinton/MatlabForSciencePaper.html] Hinton, G. E. and Salakhutdinov, R. R. Reducing the dimensionality of data with neural networks. Science 2006 | * [http://www.cs.toronto.edu/~hinton/science.pdf] [http://www.cs.toronto.edu/~hinton/MatlabForSciencePaper.html] Hinton, G. E. and Salakhutdinov, R. R. Reducing the dimensionality of data with neural networks. Science 2006 |