- W. Chan, N. Jaitly, Q. V. Le, O. Vinyals

**Listen, Attend and Spell**

arXiv 2015. [PDF] - O. Vinyals, Q.V. Le

**A Neural Conversational Model**

ICML Deep Learning Workshop, arXiv 2015. [PDF] - Q. V. Le, N. Jaitly, G. E. Hinton

**A Simple Way to Initialize Recurrent Networks of Rectified Linear Units**

arXiv 2015. [PDF] - T.M. Luong, I. Sutskever, Q.V. Le, O. Vinyals, W. Zaremba

**Addressing the Rare Word Problem in Neural Machine Translation**

ACL 2015. [PDF]

- I. Sutskever, O. Vinyals, Q. V. Le

**Sequence to Sequence Learning with Neural Networks**

NIPS 2014. [PDF] - Q.V. Le, T. Mikolov.

**Distributed Representations of Sentences and Documents**

ICML, 2014. [PDF],

- S. Bengio, J. Dean, D. Erhan, E. Ie, Q. Le, A. Rabinovich, J. Shlens, Y. Singer.

**Using Web Co-occurrence Statistics for Improving Image Categorization**

arXiv, 2013. [PDF], - R. Socher, Q. V. Le, C.D. Manning, A.Y. Ng.
**Grounded Compositional Semantics for Finding and Describing Images with Sentences**

Transactions of the Association for Computational Linguistics (TACL 2013).

also at: Deep Learning Workshop at NIPS 2013. [PDF] - T. Mikolov, Q.V. Le, I. Sutskever.
**Exploiting Similarities among Languages for Machine Translation.***arXiv*, 2013. [PDF], [Technology Review] - T. Mikolov, I. Sutskever, Q.V. Le.
**Learning the meaning behind words.***Google OpenSource Blogpost*, 2013. [Link], [Popular press] - Q.V. Le, T. Sarlos, A.J. Smola.

**Fastfood — Approximating Kernel Expansions in Loglinear Time**

*ICML*, 2013. [PDF], [PDF with Supplementary]

- M.D. Zeiler, M. Ranzato, R. Monga, M. Mao, K. Yang, Q.V. Le, P. Nguyen, A. Senior, V. Vanhoucke, J. Dean, G. Hinton.

**On Rectified Linear Units for Speech Processing**.

*IEEE International Conference on Acoustic Speech and Signal Processing (ICASSP)*, 2013. [PDF]

- J. Dean, G.S. Corrado, R. Monga, K. Chen, M. Devin, Q.V. Le, M.Z. Mao, M.A. Ranzato, A. Senior, P. Tucker, K. Yang, A. Y. Ng.

**Large Scale Distributed Deep Networks**.

*NIPS*, 2012. [PDF], [Project page]

- Q.V. Le, M.A. Ranzato, R. Monga, M. Devin, K. Chen, G.S. Corrado, J. Dean, A.Y. Ng.

**Building high-level features using large scale unsupervised learning.**

*ICML*, 2012. [PDF], [Project page]

(Large scale deep learning simulations on 10000s of cores that lead to:

- Face and cat neurons from unlabeled data,

- State-of-the-art on ImageNet from raw pixels.)

Topics: Large-scale deep learning, computer vision.

Press: New York Times and others -
A.L. Maas, Q.V. Le, T.M. O'Neil, O. Vinyals, P. Nguyen, and A.Y. Ng.

**Recurrent Neural Networks for Noise Reduction in Robust ASR**.

Interspeech 2012. [Preprint]

- Q.V. Le, J. Han, J.W. Gray, P.T. Spellman, A. Borowsky, and B. Parvin

**Learning Invariant Features of Tumor Signatures**.

*ISBI*, 2012. [PDF]

Topics: neural networks, unsupervised feature learning, RICA, computer vision

- Q.V. Le, A. Karpenko, J. Ngiam, A.Y. Ng.

**ICA with Reconstruction Cost for Efficient**.

Overcomplete Feature Learning

*NIPS*, 2011. [PDF], [Appendix], [Code],

Topics: neural networks, unsupervised feature learning, ICA, computer vision - Q.V. Le, J. Ngiam, A. Coates, A. Lahiri, B. Prochnow, A.Y. Ng.

**On optimization methods for deep learning**.

*ICML*, 2011. [PDF], [Supplementary document], [More info]

Topics: neural networks, optimization - Q.V. Le, W.Y. Zou, S.Y. Yeung, A.Y. Ng.

**Learning hierarchical spatio-temporal features for action recognition**.

with independent subspace analysis

*CVPR*, 2011. [PDF] (Oral presentation [Slides])

[Appendix], [Code], [More Info].

The code can let you train features on your unlabelled dataset.

But if you do not want to train your features, you can

download features on already trained on Hollywood2 [Features]

Topics: neural networks, unsupervised learning, action recognition, invariances

- Quoc V. Le, Morgan Quigley, Jean Feng, Justin Chen, Will Y. Zou, Marc Rasi, Tiffany Low, Andrew Y. Ng
**Haptic Belt with Pedestrian Detection**.*NIPS*, 2011 (Demonstrations). [Videos]

- Q.V. Le, J. Ngiam, Z. Chen, D. Chia, P. Koh, A.Y. Ng

**Tiled Convolutional Neural Networks**.*NIPS*, 2010. [PDF]

[TCNN code], [Invariance visualization].

NIPS poster [PPT], [PNG]

Topics: neural networks, unsupervised learning, Topographic ICA, object recognition. - Q.V. Le, A. Saxena, A.Y. Ng

**Active Perception: Interactive Manipulation for Improving Object Detection**.*Technical Report*, 2010. [PDF]

Topics: computer vision, robotics. - D. Rao, Q.V. Le, T. Phoka, M. Quigley, A. Sudsang, A.Y. Ng

**Grasping Novel Objects with Depth Segmentation***IROS*, 2010. [PDF] [Video]

Topics: robotic grasping. - M. Quigley, R. Brewer, S. P. Soudararaj, V. Pradeep, Q. Le, and A. Y. Ng
**Low-cost Accelerometers for Robotic Manipulator Perception**.*IROS*, 2010 [PDF]

Topics: robotic calibration, optimization, grasping. - Q.V. Le, D. Kamm, A. Kara, and A. Y. Ng

**Learning to grasp objects with multiple contact points**.*ICRA*, 2010. [PDF] [Video] [Slides]

Topics: robotic grasping. - C.H. Teo, S.V.N. Vishwanathan, A. Smola, Q.V. Le.
**Bundle Methods for Regularized Risk Minimization**.*JMLR*, 2010. [PDF] [Code]

Topics: learning and large-scale optimization.

Notes: previous shorter versions appeared in KDD and NIPS with Appendix

- I.J. Goodfellow, Q.V. Le, A.M. Saxe, H. Lee, A.Y. Ng,

**Measuring invariances in deep networks**.*NIPS*, 2009. [PDF]

Topics: invariances, unsupervised learning, neural networks. - A. Coates, P. Baumstarck, Q. Le, and A. Y. Ng

**Scalable Learning for Object Detection with GPU Hardware**.*IROS*, 2009. [PDF]

Topics: object detection, special hardware, GPUs. - Q.V. Le, A.Y. Ng.
**Joint calibration of multiple sensors**.*IROS*, 2009. [PDF]

Topics: robotic sensor calibration. - N. Quadrianto, A.J. Smola, T.S. Caetano, Q.V. Le
**Estimating Labels from Label Proportions**.*JMLR*, 2009. [PDF]

Topics: Gaussian Process classification, transduction, semi-supervised learning, prior knowledge.

Notes: a previous shorter version appeared in ICML - M. Quigley, S. Batra, S. Gould, E. Klingbeil, Q.V. Le, A. Wellman, A.Y. Ng.
**High Accuracy 3D Sensing for Mobile Manipulation: Improving Object Detection and Door Opening**.*ICRA*, 2009. [PDF]

Topics: 3D sensing hardware, object detection, manipulation. - C.B. Do, Q.V. Le, C.S. Foo.
**Proximal regularization for online and batch learning**.*ICML*, 2009. [PDF (conference version)] [PDF (extended version, with proofs)] [Code]

Topics: learning and optimization. - T.S. Caetano, J.J. McAuley, L. Cheng, Q.V. Le, A.J. Smola.
**Learning Graph Matching**.*PAMI*, 2009. [PDF], [Digital library link], [Code]

Topics: graph matching, structured estimation. - C.B. Do, Q.V. Le, C.H. Teo, O. Chapelle, A.J. Smola.
**Tighter Bounds for Structured Estimation**.*NIPS 21*, 2009. [PDF]

Topics: structured estimation, computational biology, ranking.

- M. Quigley, S. Batra, S. Gould, E. Klingbeil, Q.V. Le, A. Y. Ng.
**High-Accuracy 3D Sensing for Mobile Manipulators**.*NIPS 21*, 2009 (Demonstrations). [Videos], [Poster]

- N. Quadrianto, A. J. Smola, T. S. Caetano, Q. V. Le.
**Estimating Labels from Label Proportions**.*ICML*, 2008. [PDF]

Topics: Gaussian Process classification, transduction, semi-supervised learning, prior knowledge. - M. Weimer, A. Karatzoglou, Q.V. Le, A.J. Smola.
**COFI RANK - Maximum Margin Matrix Factorization for Collaborative Ranking.***NIPS 20*, 2008. [PDF] [Code/Website]

Topics: ranking, collaborative-filtering, structured outputs, optimization. - A.J. Smola, S.V.N. Vishwanathan, Q.V. Le.
**Bundle methods for machine learning.***NIPS 20*, 2008. [PDF] [Appendix], [NIPS spotlight], [Code]

Topics: optimization, theory.

- C. Burges, R. Ragno, Q. V. Le.
**Learning to Rank with nonsmooth cost functions**.*NIPS 19*, 2007. [PDF]

Topics: ranking, neural networks. - O. Chapelle, Q.V. Le, A.J. Smola.
**Large margin optimization of ranking measures.***NIPS Workshop: Machine Learning for Web Search, 2007.*[PDF][Updated technical report PDF (2009)]

Topics: ranking, structured outputs. - Q.V. Le, A.J. Smola.
**Direct optimization or ranking measures**.*NICTA Tech report,*2007. [PDF]

Topics: ranking, structured outputs. - T. Caetano, L. Cheng, Q.V. Le, A.J. Smola.
**Learning graph matching**.*ICCV,*2007. [PDF], [Oral presentation], [Code]

Topics: graph matching, max-margin structured outputs, vision. - C.H. Teo, Q.V. Le, A.J. Smola, SVN Vishwanathan.
**A Scalable Modular Convex Solver for Regularized Risk Minimization**.*KDD,*2007. [PDF], [Code]

Topics: large-scale optimization, open-source software.

- Q. V. Le, A. J. Smola, T. Gärtner, Y. Altun.
**Transductive Gaussian Process Regression with Automatic Model Selection**.*ECML*, 2006.**Best paper award**, [PDF]

Topics: Gaussian Process regression, transduction. - Q. V. Le, A. J. Smola, T. Gärtner.
**Simpler knowledge-based Support Vector Machines**.*ICML*, 2006. [PDF]

Topics: prior knowledge, non-convex optimization. - T. Gärtner, Q. V. Le, S. Burton, A. J. Smola, S. V. N. Vishwanathan.
**Large-Scale Multiclass Transduction**.*NIPS 18*, 2006. [PDF]

Topics: Gaussian Process classification, multiclass, transduction. - Q. V. Le, A. J. Smola, S. Canu.
**Heteroscedastic Gaussian Process Regression**.*ICML*, 2005. [PDF]

Topics: Gaussian Process regression. - I. Takeuchi, Q. V. Le, T. Sears, A. J. Smola.
**Nonparametric quantile estimation**.*JMLR 7*, 2006. [old PDF], [PDF], [Code(ELEFANT)]

Topics: quantile estimation, median estimation, theory. - Q. V. Le, T. Sears, A. J. Smola.

**Nonparametric quantile estimation**.*NICTA Technical report*, 2005. [PDF]

Topics: quantile estimation, median estimation, theory. - T. Gärtner, T. Horvath, Q. V. Le, A. J. Smola, S. Wrobel.
**Kernel Methods for Graphs**.*Mining Graph Data*(Book chapter). L. Holder, D. Cook (editors), 2005.

Topics: Gaussian Process classification, graphs. - T. Gärtner, Q. V. Le, A. J. Smola.
**A Short Tour of Kernel Methods for Graphs**.*Tech report*. 2006. [PDF]

Topics: Gaussian Process classification, graphs.