Journals

Dumitru Erhan, Yoshua Bengio, Aaron Courville, Pierre-Antoine Manzagol, Pascal Vincent, and Samy Bengio. Why Does Unsupervised Pre-training Help Deep Learning? Journal of Machine Learning Research, 11(Feb):625−660, 2010

Dumitru Erhan, Pierre-Jean L'Heureux, Yoshua Bengio, and Shi Yi Yue. Collaborative filtering on a family of biological targets. Journal of Chemical Information and Modeling, volume 46 , number 2, pages 626 - 635, 2006

James Bergstra, Norman Casagrande, Dumitru Erhan, Douglas Eck, and Balazs Kegl. Aggregate features and AdaBoost for music classification. Machine Learning, volume 65, issue 2-3, December 2006

Conference proceedings

Dumitru Erhan, Aaron Courville, Yoshua Bengio, and Pascal Vincent. Why Does Unsupervised Pre-training Help Deep Learning? In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS) 2010, Chia Laguna Resort, Sardinia, Italy.

Dumitru Erhan, Pierre-Antoine Manzagol, Yoshua Bengio, Samy Bengio, and Pascal Vincent. The Difficulty of Training Deep Architectures and the effect of Unsupervised Pre-Training. In Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, April 16-18, 2009, Clearwater Beach, Florida USA.

Hugo Larochelle, Dumitru Erhan, and Pascal Vincent. Deep Learning using Robust Interdependent Codes. In Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics (AISTATS 2009), April 16-18, 2009, Clearwater Beach, Florida USA.

Hugo Larochelle, Dumitru Erhan, and Yoshua Bengio. Zero-data Learning of New Tasks. In the Proceedings of the Twenty Third AAAI conference on Artificial Intelligence (AISTATS 2009), Chicago (IL), USA. Main Technical Track (AAAI), 2008.

Hugo Larochelle, Dumitru Erhan, Aaron Courville, James Bergstra and Yoshua Bengio. An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation. In the Proceedings of the 24th International Conference on Machine Learning (ICML 2007), pages 473--480. Corvallis, OR , 2007.

Posters & Presentations

Dumitru Erhan, Aaron Courville, Yoshua Bengio, Pierre-Antoine Manzagol, Samy Bengio, and Pascal Vincent. Why Does Unsupervised Pre-training Help Deep Discriminant Learning? (slides). Contributed Talk at the NIPS 2009 Workshop on The Generative and Discriminative Learning Interface, Whistler (BC), Canada, December 2009.

Dumitru Erhan, Aaron Courville, Yoshua Bengio, and Pascal Vincent. Visualizing Higher Layer Features of a Deep Network. Spotlight presentation and poster at the ICML 2009 Workshop on Learning Feature Hierarchies, Montréal, Canada.

Aaron Courville, Dumitru Erhan, Pascal Vincent, and Yoshua Bengio. Sparse Covariance Coding. Poster presentation at the Learning Workshop ("Snowbird"), Snowbird, Utah, April 2008.

Hugo Larochelle, Dumitru Erhan, and Yoshua Bengio. Generalization to a zero-data task: an empirical study. Oral presentation (by Hugo Larochelle) at the Learning Workshop ("Snowbird"), San Juan, Puerto Rico, March 2007

Dumitru Erhan, Pierre-Jean L'Heureux, Yoshua Bengio, and Shi Yi Yue. Collaborative filtering on a family of biological targets. Presented at the 230th ACS National Meeting, in Washington, DC, 2005.

Pierre-Jean L Heureux, Olivier Delalleau, Dumitru Erhan, Yoshua Bengio, and Shi Yi Yue. A neural network application in multi-target QSAR. Presented at the 7th International Conference on Chemical Structures, Noordwijkerhout, The Netherlands, 2005.

Technical Reports

Dumitru Erhan, Aaron Courville, and Yoshua Bengio. Understanding Representations Learned in Deep Architectures. Technical Report 1355, DIRO, Université de Montré.

Dumitru Erhan, Aaron Courville, Yoshua Bengio, and Pascal Vincent. Visualizing Higher Layer Features of a Deep Network. Technical Report 1341, DIRO, Université de Montral

Dumitru Erhan, Yoshua Bengio, Pierre-Jean L'Heureux, and Shi Yi Yue. Generalizing to a zero-data task: a computational chemistry case study. Technical Report 1286, Département d'informatique et recherche opérationnelle, University of Montreal, Montreal, Canada, 2006.

Theses

Dumitru Erhan. Collaborative filtering techniques for drug discovery. M.Sc. Thesis. University of Montreal, Montreal, Canada, 2006.

Dumitru Erhan. Exploration of combining ESN learning with gradient-descent Recurrent Neural Network learning techniques. Unpublished Bachelor's Thesis, International University Bremen, Bremen, Germany, 2004.