Bayes group

We have studied variational Bayesian learning and applied it to various latent variable model structures which are suited to unsupervised learning. (See glossary for explanation of terms). We are mainly interested in models with continuous variables.

Research of the Bayes group

On our research page, you can find descriptions of our research topics. The Bayes chapter of the biennial report of our Adaptive Informatics Research Centre covering the years 2008-2009 also contains extended summaries on our recent research results with references.

Members

The Bayes group has 11 members and it is lead by prof. Juha Karhunen.

Publications

On our publication page, you can find the most important publications of our Bayes group downloadable in electronic form.

Software

Here you can find free software packages prepared by the Bayes group. They include Bayes blocks and their extensions, programmed in C++ and Python, as well as Matlab packages for nonlinear factor analysis and nonlinear dynamical factor analysis.

Courses

• T-61.3050 Machine Learning: Basic Principles
• T-61.5130 Machine Learning and Neural Networks
• T-61.5140 Machine Learning: Advanced Probabilistic Methods

Figure caption

The figure on the right shows an example of the gravitational lensing phenomenon in astronomy, where several images of the source are observed. We have applied our Bayesian methods to the delay estimation problem appearing in this application. See "Applications to astronomy" on our "Research" subspage for a more detailed explanation.