Information-Theoretic Machine Learning & Data Mining Group

日本語版

Welcome to the webpage of Information-Theoretic Machine Learning and Data Mining Group. We are part of the Department of Mathemacical Informatics at the University of Tokyo. We are interested in designing and analyzing computational techniques for discovering patterns and making quantitative predictions on massive, heterogeneous, and dynamic real world data.

Research Topics

• Fundamental techniques and theory of machine learning
  • Information theoretic approach (MDL, stochastic complexity, ...)
  • Model selection
  • Distributed cooperative learning
  • Learning network structures
• Basic techniques for data mining
  • Anomaly detection
  • Network dynamics miniming
  • Latent dynamics mining
• Application of data mining
  • Computer security
  • Marketing
  • Web analytics
  • Process monitoring

• Read more