Honglak Lee

Assistant Professor
Computer Science & Engineering Division
Electrical Engineering and Computer Science Department
University of Michigan, Ann Arbor

Education
Ph.D. in Computer Science, Stanford University, 2010
Curriculum Vitae

Research
My research interests lie in machine learning and its application to a range of perception problems in the fields of artificial intelligence, such as computer vision, robotics, audio recognition, and text processing. I am particularly interested in developing algorithms for automatically learning feature representations from unlabeled data. I am also interested in data mining, probabilistic graphical models, convex optimization, high-dimensional data analysis, and large-scale learning using massive datasets.

Teaching
EECS 598: Unsupervised Feature Learning, Fall 2010
EECS 545: Machine Learning, Winter 2011
EECS 203: Discrete Mathematics, Fall 2011
EECS 545: Machine Learning, Winter 2012

Professional Activities

Program Committee / Reviewer: ICML 2009, 2010, 2011, 2012; NIPS 2010, 2011, 2012; UAI 2009; AISTATS 2011, 2012; ECCV 2010, 2012; CVPR 2010, 2011, 2012; ICCV 2011.
Journal Reviewer: Journal of Machine Learning Research (JMLR); Neural Computation; IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE-TPAMI); IEEE Transactions on Knowledge and Data Engineering (IEEE-TKDE); IEEE Transactions on Audio, Speech and Language Processing (IEEE-TASL); ACM Transactions on Intelligent Systems and Technology (ACM TIST); Proceedings of the IEEE.

News

I am currently recruiting strong and motivated students. If you are a student at University of Michigan and have interest in getting involved with research, please send me an email. If you are not a UM student, then please apply to the CSE PhD program. Also, please read this document for more information.
I co-organized NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning (with Yoshua Bengio, Geoffrey Hinton, Yann LeCun, Andrew Ng, and Marc'Aurelio Ranzato).
I co-organized ICML 2011 Workshop on Learning Architectures, Representations, and Optimization for Speech and Visual Information Processing (with Li Deng and Kai Yu).
I received a Google Faculty Research Award.
I am a guest editor of TPAMI Special Issue on "Learning Deep Architectures." See the call for paper here.
I will co-organize a CVPR 2012 Tutorial on Deep Learning Methods for Computer Vision (with Rob Fergus, Marc'Aurelio Ranzato, Ruslan Salakhutdinov, Graham Taylor, and Kai Yu).
We give warm thanks for the support from Google, Toyota, and UM Medical Innovation Center.

Contact Information
Address:
Room 3773, Beyster Building
2260 Hayward Street
Ann Arbor, MI 48109

Email:

Publications

Learning Local Transformation Invariance with Restricted Boltzmann Machines
Kihyuk Sohn and Honglak Lee.
To appear in ICML, 2012.

Learning Hierarchical Representations for Face Verification with Convolutional Deep Belief Networks.
Gary Huang, Honglak Lee, and Erik Learned-Miller.
To appear in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012. [pdf]

An Efficient Branch-and-Bound Algorithm for Optimal Human Pose Estimation.
Min Sun, Murali Telaprolu, Honglak Lee, and Silvio Savarese.
To appear in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012. [pdf]

Online Incremental Feature Learning with Denoising Autoencoders.
Guanyu Zhou, Kihyuk Sohn, and Honglak Lee.
In Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR W&CP 22, 2012. [pdf] [supplementary material] (oral presentation)
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011.)

Efficient Distributed Linear Classification Algorithms via the Alternating Direction Method of Multipliers.
Caoxie Zhang, Honglak Lee, and Kang G. Shin.
In Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR W&CP 22, 2012. [pdf] [code]

Eﬃcient and Exact MAP-MRF Inference using Branch and Bound.
Min Sun, Murali Telaprolu, Honglak Lee, and Silvio Savarese.
In Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR W&CP 22, 2012. [pdf] [supplementary material] [code]

Efficient Learning of Sparse, Distributed, Convolutional Feature Representations for Object Recognition.
Kihyuk Sohn, Dae Yon Jung, Honglak Lee, and Alfred Hero III.
In Proceedings of 13th International Conference on Computer Vision (ICCV), 2011. [pdf] [bib]

Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks.
Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y. Ng.
Communications of the ACM, vol. 54, no. 10, pp. 95-103, 2011. [pdf] [bib] [fulltext] [technical perspective by Geoffrey Hinton]
Research Highlights.

A classification-based polyphonic piano transcription approach using learned feature representations.
Juhan Nam, Jiquan Ngiam, Honglak Lee, and Malcolm Slaney.
In Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR), 2011. [pdf] [bib]

Multimodal Deep Learning.
Jiquan Ngiam, Aditya Khosla, Mingyu Kim, Juhan Nam, Honglak Lee and Andrew Y. Ng.
In Proceedings of the 29th International Conference on Machine Learning (ICML), 2011. [pdf] [bib]
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2010. [pdf])

An Analysis of Single-Layer Networks in Unsupervised Feature Learning.
Adam Coates, Honglak Lee and Andrew Y. Ng.
In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), JMLR W&CP 15, 2011. [pdf] [bib] [code] [STL-10 dataset]
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2010. [pdf])

Unsupervised Feature Learning Via Sparse Hierarchical Representations.
Honglak Lee
Ph.D. Dissertation, Stanford University, Computer Science Department, August 2010. [pdf] [bib]

An integrated machine learning approach to stroke prediction.
Aditya Khosla, Yu Cao, Cliff Chiung-Yu Lin, Hsu-Kuang Chiu, Junling Hu, and Honglak Lee.
Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2010. [pdf] [bib]

Unsupervised feature learning for audio classification using convolutional deep belief networks.
Honglak Lee, Yan Largman, Peter Pham, and Andrew Y. Ng.
Advances in Neural Information Processing Systems (NIPS) 22, 2010. [pdf] [bib]

Measuring invariances in deep networks.
Ian J. Goodfellow, Quoc V. Le, Andrew M. Saxe, Honglak Lee, and Andrew Y. Ng.
Advances in Neural Information Processing Systems (NIPS) 22, 2010. [pdf] [bib]

Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations.
Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y. Ng.
In Proceedings of the 26th International Conference on Machine Learning (ICML), 2009. [pdf] [bib] [talk video]
Best Paper Award: Best Application Paper.

Exponential Family Sparse Coding with Application to Self-taught Learning.
Honglak Lee, Rajat Raina, Alex Teichman, and Andrew Y. Ng.
In Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI), 2009. [pdf] [bib]

Sparse deep belief net model for visual area V2.
Honglak Lee, Chaitu Ekanadham, and Andrew Y. Ng.
Advances in Neural Information Processing Systems (NIPS) 20, 2008. [pdf] [bib]

Self-taught learning: Transfer learning from unlabeled data.
Rajat Raina, Alexis Battle, Honglak Lee, Benjamin Packer, and Andrew Y. Ng.
In Proceedings of the 24th International Conference on Machine Learning (ICML), 2007. [pdf] [bib]

Efficient sparse coding algorithms.
Honglak Lee, Alexis Battle, Rajat Raina, and Andrew Y. Ng.
Advances in Neural Information Processing Systems (NIPS) 19, 2007. [pdf] [bib] [code]

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, pp. 584-592 (2007). [pdf] [fulltext] [pubmed]

Efficient L1 regularized logistic regression.
Su-In Lee, Honglak Lee, Pieter Abbeel, and Andrew Y. Ng.
In Proceedings of the 21st National Conference on Artificial Intelligence (AAAI), 2006. [pdf] [bib] [code]

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

A dynamic Bayesian network model for autonomous 3d reconstruction from a single indoor image.
Erick Delage, Honglak Lee, and Andrew Y. Ng.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2006. [pdf] [bib] [experiments]

Automatic single-image 3d reconstructions of indoor Manhattan world scenes.
Erick Delage, Honglak Lee, and Andrew Y. Ng.
In Proceedings of the 12th International Symposium of Robotics Research (ISRR), 2005. [pdf] [bib] [experiments]

Spam deobfuscation using a hidden Markov model.
Honglak Lee and Andrew Y. Ng.
In Proceedings of the Second Conference on Email and Anti-Spam (CEAS), 2005. [pdf] [bib]
Best Student Paper Award.