I am a ph.d 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.

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

kihyuks [at] umich [dot] edu
kihyuk.sohn [at] gmail [dot] com

Rm 3856, Bob and Betty Beyster Building,
2260 Hayward Street,
Ann Arbor, MI 48109-2121

  • Our paper "Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling" got accepted to CVPR 2013. [pdf][project page]
  • Our paper "Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines" got accepted to ICML 2013. [pdf][project page]
  • I have presented "Jointly Learning and Selecting Features via Conditional Point-wise Mixture Restricted Boltzmann Machines" at deep learning workshop held in conjunction with NIPS 2012.