I'm a machine learning researcher and computer engineer. I'm currently finishing my Ph.D. at U. of Montréal on deep learning algorithms for large-scale problems.
Curriculum Vitae: PDF
Here are some my research publications in peer-reviewed conferences and journals:
Y. Dauphin, R. Pascanu, C. Gulcehre, K. Cho, S. Ganguli, Y. Bengio. Identifying and attacking the saddle point problem in high-dimensional non-convex optimization. To appear in Advances in Neural Information Processing Systems 26 (NIPS 2014).
Y. Dauphin, G. Tur, D. Hakkani-Tur, L. Heck. Zero-Shot Learning and Clustering for Semantic Utterance Classification. In Proceedings of the International Conference on Learning Representations (ICLR 2014).
Y. Dauphin, Y. Bengio. Stochastic Ratio Matching of RBMs for Sparse High-Dimensional Inputs. In Advances in Neural Information Processing Systems 26 (NIPS 2013).
S. Kanou, et al. Combining modality specific deep neural networks for emotion recognition in video. In Proceedings of the 15th ACM on International conference on multimodal interaction (ICMI 2013).
Y. Bengio, G. Mesnil, Y. Dauphin, S. Rifai. Better Mixing via Deep Representations. In Proceedings of the 30th International Conference on Machine Learning (ICML 2013).
S. Rifai, Y. Bengio, Y. Dauphin, P. Vincent. A Generative Process for Sampling Contractive Auto-Encoders. In Proceedings of the 29th International Conference on Machine Learning (ICML 2012).
S. Rifai, Y. Dauphin, P. Vincent, Y. Bengio, X. Muller. The Manifold Tangent Classifier. In Advances in Neural Information Processing Systems (NIPS 2011). Invited as plenary Talk. Best student paper award: Honourable mention.
Y. Dauphin, X. Glorot, Y. Bengio. Large-Scale Learning of Embeddings with Reconstruction Sampling. In Proceedings of the 28th International Conference on Machine Learning (ICML 2011).
S. Rifai, G. Mesnil, P. Vincent, X. Muller, Y. Bengio, Y. Dauphin, X. Glorot. Higher Order Contractive Auto-Encoder. In Proceedings of the European Conference on Machine Learning (ECML 2011).
G. Mesnil, Y. Dauphin, X. Glorot, S. Rifai, Y. Bengio, et al. Unsupervised and Transfer Learning Challenge: a Deep Learning approach. In Journal of Machine Learning Workshop and Conference Papers (JMLR W&CP 2011).
At the Neural Information Processing Systems (NIPS) 2011.
At the International Conference on Machine Learning (ICML) 2011.
Here are some of my work experiences (check my CV for the full list):
Tags: Deep Neural Networks, Spoken Language Understanding, Natural Language Processing
I was a research intern in the summer of 2013 to apply deep learning to the problem of Spoken Language Understanding, specifically domain classification and semantic parsing.
Tags: Deep Neural Networks, Speech
I was hired as an intern in the summer of 2012 to do research on deep learning algorithms for Automatic Speech Recognition (ASR). This is for an application that is deployed on every Android phone: Voice Search.
Here are some my open source contributions (check my CV for the full list):
Tags: JIT compilation, Common Lisp
In 2007, I started working on a Just-in-Time (JIT) compiler for the open source CLisp Virtual Machine. I started development on my own because I wanted to make CLisp faster. I am now an official member of the CLisp team.
Started in the autumn of 2007. Development is ongoing.
Tags: Algorithms, Image processing, Creativity
I was amazed by a post written by Roger Alsing. He made an algorithm that could reproduce images using a limited amount of semi-transparent polygons. I wanted to make my own.