Probabilistic Learning Research Group at BI Lab

The Probabilistic Learning Research Group at Biointelligence Lab investigates machine learning algorithms for probabilistic graphical models such as hierarchical Bayesian networks (HBN) and self-organizing latent lattice models (SOLL). Our current research focuses on structural learning of large-scale probabilistic graphical models in a noisy and/or dynamic environment. For example, we are developing methods for learning large-scale Bayesian networks (having more than 10,000 nodes) from sparse datasets. Major application areas of these techniques include text mining and multi-modal associative information analysis.

Upcoming Conferences on Probabilistic Graphical Models

  • ICML 2012, The 29th International Conference on Machine Learning, June 26 ~ July 1, 2012, Edinburgh, Scotland.
  • UAI 2012, The 28th Conference on Uncertainty in Artificial Intelligence, August 15 ~ 17, 2012, Catalina Island, California, USA.
  • ECML/PKDD 2012, The 23rd European Conference on Machine Learning / The 16th Practice of Knowledge Discovery in Databases, Sep. 24 ~ 28, 2012, Bristol, UK.
  • NIPS 2012, The 26th Conference on Neural Information Processing Systems, 3 ~ 8, 2012, Lake Tahoe, Nevada, United States.

Seminars

Invited Talks

Tutorials

Research Projects

  • Videome, Cognitive Machine Learning from Digital Videos
  • MARS: A Multimodal Associative Recommendation System
  • DNAChipBench (NRL Project): Intelligent Design and Analysis Technology for DNA Chip
  • BrainGene: DNA data mining for the analysis of expression patterns of vertebrate brain development-specific genes (rat)
  • LaText: Text mining based on latent variable models
  • MrHumor: A personalized Internet agent that recommends humors and jokes

Publications

Useful links


This page is maintained by Byoung-Hee Kim
Last Update: October 15, 2012.