Kihyuk Sohn

PhD candidate
Electrical Engineering and Computer Science Department 
University of Michigan, Ann Arbor

Research
I am a PhD candidate in machine learning group at University of Michigan advised by professor Honglak Lee. I have broad interest in machine learning and computer vision. Specifically, my research focuses on unsupervised feature learning and deep learning toward learning a "better" feature representation that can be easily adopted to wide range of domains.


Education
Curriculum Vitae [pdf]

2008.09 ~ current
    University of Michigan, Ann Arbor, MI
    Ph.D. student in the department of Electrical Engineering and Computer Science: Systems
    Thesis advisor : Professor Honglak Lee
2003.03 ~ 2008.02
    Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea
    B.S. in Electrical Engineering and Computer Science and Mathematical Science


Contact information
Email:
    kihyuks [at] umich [dot] edu
    kihyuk.sohn [at] gmail [dot] com
Address:
    Rm 3856, Bob and Betty Beyster Building,
    2260 Hayward Street,
    Ann Arbor, MI 48109-2121


News
  • Our paper "Improved Multimodal Deep Learning with Variation of Information" got accepted to NIPS 2014. [pdf][bib]
  • Our paper "Learning to Disentangle Factors of Variation with Manifold Interaction" got accepted to ICML 2014. [pdf][bib][code]
  • Our paper "Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling" got accepted to CVPR 2013. [pdf][bib][project page][code]
  • Our paper "Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines" got accepted to ICML 2013. [pdf][bib][supplementary material][project page][code]

Publications

[8] Improved Multimodal Deep Learning with Variation of Information.
Kihyuk Sohn, Wenling Shang and Honglak Lee
To appear in Advances in Neural Information Processing Systems (NIPS), 2014 [pdf][bib]

[7] Learning to Disentangle Factors of Variation with Manifold Interaction.
Scott Reed, Kihyuk Sohn, Yuting Zhang and Honglak Lee
In Proceedings of the 31st International Conference on Machine Learning (ICML), 2014. [pdf][bib][code]

[6] Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling.
Andrew Kae*, Kihyuk Sohn*, Honglak Lee and Erik Learned-Miller.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013. [pdf][bib][project page][code] (* indicates equal contribution.)

[5] Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines.
Kihyuk Sohn, Guanyu Zhou, Chansoo Lee, and Honglak Lee.
In Proceedings of the 30th International Conference on Machine Learning (ICML), 2013. [pdf][bib][supplementary material][project page][code]
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2012.)

[4] Learning Invariant Representations with Local Transformations.
Kihyuk Sohn and Honglak Lee.
In Proceedings of the 29th International Conference on Machine Learning (ICML), 2012. [pdf][bib]

[3] 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][bib][supplementary material] (oral presentation)
(A previous version was presented at the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011.)

[2] An interpretation of the Cover and Leung capacity region for the MAC with feedback through stochastic control.
Achilleas Anastasopoulos and Kihyuk Sohn.
In Proceedings of IEEE International Conference on Communications (ICC), 2012. [pdf][bib]

[1] 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]



Software