Publications

Here is a list of my recent publications (in reverse chronological order). It’s not entirely complete, so if you can’t find what you’re looking for, please let me know.

  • Chung, J., Kastner, K., Dinh, L., Goel, K., Courville, A., Bengio, Y. (2015) A Recurrent Latent Variable Model for Sequential DataarXiv:1506.02216. [pdf]
  • Yao, L., Torabi, A, Cho, K., Ballas, N., Pal, C., Larochelle, H., Courville, A. (2015) Describing Videos by Exploiting Temporal StructurearXiv:1502.08029. [pdf]
  • Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., Bengio, Y. (2015)  Show, Attend and Tell: Neural Image Caption Generation with Visual AttentionProceedings of the 32nd International Conference on Machine Learning. [abstract][pdf][supplemental(pdf)]
  • Goodfellow, I.J., Pouget-Abadie, J., Mirza, M.,  Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y. (2014) Generative Adversarial Nets. Advances in Neural Information Processing Systems. [pdf]
  • Dumoulin, V., Goodfellow, I.J., Courville, A., Bengio, Y. (2014) On the Challenges of Physical Implementations of RBMs. Proceedings of the 28th AAAI Conference on Artificial Intelligence. [arXiv version pdf]
  • Warde-Farley, D., Goodfellow, I.J., Courville, A., Bengio, Y. (2014) An empirical analysis of dropout in piecewise linear networks. Proceedings of the 2nd International Conference on Learning Representations (ICLR). [pdf]
  • Goodfellow, I.J., Mirza, M., Da, X., Courville, A., Bengio, Y. (2014) An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks. Proceedings of the 2nd International Conference on Learning Representations (ICLR).[pdf]
  • Kanou, S.,E., Pal, C., Bouthillier, X., Froumenty, P., Gülçehre, C., Memisevic, R., Vincent, P.,  Courville, A., Bengio, Y., Ferrari, R.C., Mirza, M., Jean, S., Carrier, P.-L., Dauphin, Y., Boulanger-Lewandowski, N., Aggarwal, A., Zumer, J., Lamblin, P., Raymond, J.-P., Desjardins, G., Pascanu, R., Warde-Farley, D., Torabi, A., Sharma, A., Bengio, E., Konda, K.R., Wu, Z. (2013) Combining modality specific deep neural networks for emotion recognition in video. Proceedings of the 15th ACM on International conference on multimodal interaction, pp. 543-550. [pdf]
  • Bengio, Y., Léonard, N., Courville, A. (2013) Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. arXiv preprint arXiv:1308.3432 [pdf]
  • Goodfellow,I.J., Mirza, M., Courville, A., Bengio, Y. (2013) Multi-prediction deep Boltzmann machines. Advances in Neural Information Processing Systems, 548-556. [pdf][bibtex]
  • Messing, R., Torabi, A., Courville, A., Pal C. (2013) Evaluating and Extending Trajectory Features for Activity Recognition. Advanced Topics in Computer Vision (Chapter 4, pp. 95-111).
  • Bengio, Y., Courville, A., Vincent, P. (2013) Represenation Learning: A Review and New Perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Special Issue. [arXiv version]
  • Goodfellow, I.J., Courville, A., Bengio, Y. (2013) Scaling up Spike-and-Slab Models for Unsupervised Feature Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Special Issue. [pdf]
  • Goodfellow, I., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y. (2013) Maxout Networks. Proceedings of the 30th International Conference on Machine Learning (ICML).[pdf]
  • Luo, H., Carrier, P.L., Courville, A., Bengio, Y. (2013) Texture Modeling with Convolutional Spike-and-Slab RBMs and Deep Extensions. Proceedings of the 16th International Conference on Artificial Intelligence and Statistics (AISTATS). [pdf]
  • Desjardins, G., Pascanu, R., Courville, A., Bengio, Y. (2013) Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines. Proceedings of the 1st International Conference on Learning Representations (ICLR).[pdf]
  • Rifai, S., Bengio, Y., Courville, A., Mirza, M., Vincent, P. (2012) Disentangling factors of variation for facial expression recognition. Proceedings of the 12th European Conference on Computer Vision.[pdf][bibtex]
  • Goodfellow, I.J., Courville, A., Bengio, Y. (2012) Large-Scale Feature Learning With Spike-and-Slab Sparse Coding. Proceedings of the 29th International Conference on Machine Learning.[pdf][bibtex][video of talk]
  • Desjardins, G., Courville, A., Bengio, Y. (2011) On Tracking The Partition Function. Advances in Neural Information Processing Systems 24.[pdf][bibtex][supplemental]
  • Bergstra, J., Courville, A., Bengio, Y. (2011) The Statistical Inefficiency of Sparse Coding for Images (or, One Gabor to Rule them All). Technical report 1109.6638v2, arXiv.  [pdf][bibtex]
  • Courville, A., Bergstra, J., Bengio, Y. (2011) Unsupervised Models of Images by Spike-and-Slab RBMs. Proceedings of the 28th International Conference on Machine Learning: 1145–1152.  [pdf][bibtex]
  • Courville, A., Bergstra, J., Bengio, Y. (2011) The Spike and Slab Restricted Boltzmann Machine. Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS): 233–241.  [abs][pdf]  Poster winner of the “People’s Choice Award”.
  • Bengio, Y., Courville, A. (2011) Deep Learning of Representations. Chapter in Handbook on Neural Information processing; Bianchini, M., Jain, L., Maggini, M., Eds.; Springer:Berlin Heidelberg.[pdf]
  • 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., Bergstra, J. (2011) Unsupervised and Transfer Learning Challenge: a Deep Learning approach. JMLR W\& CP: Proceedings of the Unsupervised and Transfer Learning challenge and workshop.  [pdf]
  • Vincent, R.D., Courville, A., and Pineau, J. (2011) A bistable computational model of recurring epileptiform activity as observed in rodent slice preparations. Neural Networks, 24(6): 526-537.  [abs][pdf]
  • Erhan, D., Bengio, Y., Courville A., Manzagol, P.-A., Vincent, P., Bengio, S. (2010)  Why Does Unsupervised Pre-training Help Deep Learning?  Journal of Machine Learning Research, 11: 625-660.  [abs][pdf]
  • Erhan, D., Courville, A., Bengio, Y., Vincent, P. (2010) Why Does Unsupervised Pre-training Help Deep Learning?  Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS): 201-208.  [pdf]
  • Erhan, D., Courville, A., Bengio Y. (2010) Understanding Representations Learned in Deep Architectures.  Département d’Informatique et de Recherche Opérationnelle, Université de Montréal: 1355. [pdf]
  • Desjardins, G., Courville, A., Bengio, Y. (2010) Adaptive Parallel Tempering for Stochastic Maximum Likelihood Learning of RBMs.  Technical report 1012.3476v1, arXiv. [pdf][bibtex]
  • Desjardins, G., Courville, A., Bengio, Y., Vincent, P., Delalleau, O. (2010) Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines.  Proceedings of the 9th International Conference on Artificial Intelligence and Statistics (AISTATS): 145-152. [pdf]
  • Courville, A., Eck, D., Bengio, Y. (2010) An Infinite Factor Model
    Hierarchy Via a Noisy-Or Mechanism. Advances in Neural Information
    Processing Systems 22. [pdf][bibtex][supplemental]
  • Daw, N., Courville, A. (2008) The Pigeon as Particle Filter. Advances in Neural Information Processing Systems 20. [pdf]
  • Daw, N.D., Courville, A.C., Dayan, P. (2008) Semi-Rational Models of Conditioning: The Case of Trial Order.  Chapter in The Probabilistic Mind; Chater, N., Oaksford, M., Eds.; Oxford University Press: Oxford. [pdf]
  • Larochelle, H., Erhan, D., Courville, A., Bergstra, J., Bengio, Y., (2007) An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation. Proceedings of the 24th International Conference on Machine Learning: 473-480. [pdf]
  • Courville, A.C., Daw, N.D., and Touretzky, D.S. (2006) Bayesian theories of conditioning in a changing world. Trends in Cognitive Sciences, 10: 294-300. [pdf]
  • Wellington C., Courville A., Stentz A. (2006) A Generative Model of Terrain for Autonomous Navigation in Vegetation. The International Journal of Robotics Research, 25: 1287-1304. [pdf]
  • Courville, A. (2006) A Latent Cause Theory of Classical Conditioning. Ph.D. thesis, Robotics Institute, Carnegie Mellon University, Pittsburgh PA USA. [pdf]
  • Daw, N.D., Courville, A.C., Touretzky, D. (2006) Representation and timing in theories of the dopamine system. Neural Computation, 18: 1637-1677. [pdf]
  • Wellington, C., Courville, A., Stentz A. (2005) Interacting Markov Random
    Fields for Simultaneous Terrain Modeling and Obstacle Detection.
    Proceedings of Robotics: Science and Systems, I: 1-8. [abs & bibtex][pdf]
  • Courville, A.C., Daw, N.D., and Touretzky, D.S. (2005) Similarity and
    discrimination in classical conditioning: A latent variable account.
    Advances in Neural Information Processing Systems, 17: 313-320. [pdf]
  • Courville, A.C., Daw, N.D., Gordon, G.J., and Touretzky, D.S. (2004) Model uncertainty in classical conditioning. Advances in Neural Information Processing Systems, 16: 977-984. [pdf]
  • Daw, N.D., Courville, A.C., and Touretzky, D.S. (2003) Timing and partial
    observability in the dopamine system. Advances in Neural Information
    Processing Systems, 15: 99-106. [pdf]
  • Daw, N.D., Courville, A.C., and Touretzky, D.S. (2002) Dopamine and inference about timing.  Proceedings of the Second International Conference on Development and Learning: 271- 276. [pdf]
  • Courville, A. C., Touretzky, D. S. (2002) Modeling temporal structure in classical conditioning. Advances in Neural Information Processing Systems, 14: 3-10. [abs & bibtex][pdf]