Research | home | research | teaching | schedule | dance |
 

 

Research interests:

  • Machine Learning:  (probabilistic graphical models, discriminative training of probabilistic models, large margin probabilistic models, learning in natural and structured domains)
  • Computer Vision
  • Natural Language Processing
  • Bioinformatics and Computational Biology
Publications
  • Multiple label prediction for image annotation with multiple kernel correlation models. Oksana Yakhnenko and Vasant Honavar. Accepted to appear in Workshop on Visual Context Learning at CVPR 2009. [PDF]
  • Multi-Modal Hierarchical Dirichlet Process Model for Predicting Image Annotation and Image-Object Label Correspondence. Oksana Yakhnenko and Vasant Honavar. Accepted to appear in SDM 2009. [PDF][talk slides PDF]
  • KDD Cup 2008 and the Workshop on Mining Medical Data. R. Bharat Rao, Oksana Yakhnenko, Balaji Krishnapuram. SIGKDD Explorations, Volume 10, Issue 2. 2008. [PDF]
  • Annotating Images and Image Objects using a Hierarchical Dirichlet Process Model. Oksana Yakhnenko and Vasant Honavar. SIGKDD 2008, The 9th International Workshop on Multimedia Data Mining [PDF]
  • Mining the Web for Relations between Digital Devices using a Probabilistic Maximum Margin Model. Oksana Yakhnenko, Barbara Rosario (Intel Research). International Joint Conferences in Natural Language Processing (IJC-NLP 2008)[PDF][data to be posted]
  • Principled Generative-Discriminative Hybrid Hidden Markov Model. Oksana Yakhnenko, Lucian Vlad Lita, Romer Rosales, Stefan Niculescu. NIPS 2007, Workshop on Representations and Inference on Probability Distributions [extended abstract]
  • Discriminatively Trained Markov Model for Sequence Classification. Oksana Yakhnenko, Adrian Silvescu, Vasant Honavar. International Conference on Data Mining (ICDM 2005)[PDF] [talk slides PDF]
  • Visualizing effects from log-linear models. Oksana Yakhnenko, Heike Hofmann. Joint Statistical Meetings (JSM 2005).
Research Internships

  • Siemens Medical Solutions (Computer-Aided Diagnostics and Therapy) May-September 2008. Worked on breast cancer diagnosis with Balaji Krishnapuram and Vikas Raykar

  • Siemens Medical Solutions (Computer-Aided Diagnostics and Therapy) May-September 2007. Worked on named entity recognition in medical domain with Romer Rosales, Lucian Lita and Stefan Niculescu

  • Intel Research (Digital Home Group)
    May-September 2006. Worked with Barbara Rosario and Bill Schilit on relation extraction from text

Software

  • AirlDM - a collection of data-source independent learning algorithms