Honglak Lee

Ph.D. candidate

Computer Science Department

Stanford University

Stanford, CA 94305

Office: Gates Building, Room 124

Email:

---

Research Interests: Machine Learning

(Probabilistic models, vision and pattern recognition, convex optimization, and high-dimensional data analysis)

Ph.D. Advisor: Professor Andrew Ng.

---

Publications (Refereed Conference Proceedings):

Unsupervised feature learning for audio classification using convolutional deep belief networks. [pdf]

Honglak Lee, Yan Largman, Peter Pham and Andrew Y. Ng.

Advances in Neural Information Processing Systems (NIPS) 22.

Measuring invariances in deep networks. [pdf]

Ian J. Goodfellow, Quoc V. Le, Andrew M. Saxe, Honglak Lee and Andrew Y. Ng.

Advances in Neural Information Processing Systems (NIPS) 22.

Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. [pdf]

Honglak Lee, Roger Grosse, Rajesh Ranganath and Andrew Y. Ng.

Proceedings of the Twenth-Sixth International Conference on Machine Learning (ICML), 2009.

Best paper award: Best application paper.

Exponential Family Sparse Coding with Application to Self-taught Learning. [pdf]

Honglak Lee, Rajat Raina, Alex Teichman and Andrew Y. Ng.

Proceedings of the Twenth-First International Joint Conference on Artificial Intelligence (IJCAI-09), 2009.

Sparse deep belief net model for visual area V2. [pdf]

Honglak Lee, Chaitu Ekanadham, Andrew Y. Ng.

Advances in Neural Information Processing Systems (NIPS) 20, 2008.

Self-taught learning: Transfer learning from unlabeled data. [pdf]

Rajat Raina, Alexis Battle, Honglak Lee, Benjamin Packer and Andrew Y. Ng.

In Proceedings of the Twenty-fourth International Conference on Machine Learning (ICML), 2007.

Efficient sparse coding algorithms. [pdf][code]

Honglak Lee, Alexis Battle, Rajat Raina, Andrew Y. Ng.

Advances in Neural Information Processing Systems (NIPS) 19, 2007.

Efficient L1 regularized logistic regression. [pdf][code]

Su-In Lee, Honglak Lee, Pieter Abbeel and Andrew Y. Ng.

In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI), 2006.

A dynamic Bayesian network model for autonomous 3d reconstruction from a single indoor image. [pdf][experiments]

Erick Delage, Honglak Lee, and Andrew Y. Ng.

In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2006.

Quadruped robot obstacle negotiation via reinforcement learning. [pdf, videos]

Honglak Lee, Yirong Shen, Chih-Han Yu, Gurjeet Singh, and Andrew Y. Ng.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2006.

Automatic single-image 3d reconstructions of indoor Manhattan world scenes. [pdf][experiments]

Erick Delage, Honglak Lee, and Andrew Y. Ng.

In Proceedings of the 12th International Symposium of Robotics Research (ISRR), 2005.

Spam deobfuscation using a hidden Markov model. [pdf]

Honglak Lee and Andrew Y. Ng.

In Proceedings of the Second Conference on Email and Anti-Spam (CEAS), 2005.

Best student paper award.

Publications (Journals):

High-throughput identification of transcription start sites, conserved promoter motifs, and predicted regulons

Patrick T. McGrath, Honglak Lee, Li Zhang, Antonio A. Iniesta, Alison K. Hottes,

Meng How Tan, Nathan J. Hillson, Ping Hu, Lucy Shapiro, and Harley H. McAdams

Nature Biotechnology, 25, 584-592 (2007). [pdf, fulltext, pubmed]