Skip to main content

« www.hiit.fi

Home
 

Home » Research » Research groups » Neuroinformatics » Statistical theory


Search form

Home
News & events
About HIIT
Research
Research programmes
Research groups
Collaborative Networking
Combinatorial Algorithms and Computation
Combinatorial Pattern Matching
Complex Systems Computation
Computational Logic Group
Digital Content Communities
Discovery
Distributed Networking and Security
Kernel Machines, Pattern Analysis, and Computational Biology
Mobile Computing
Networking Research
Neuroinformatics
Computational Neuroscience
Statistical theory
FastICA
ICASSO
NMFsc
LiNGAM
Score matching
Analysis of neural data
New Paradigms in Computing
PURSUIT
Parsimonious Modelling
Social Interaction and Emotion
Statistical Machine Learning and Bioinformatics
Ubiquitous Interaction (UIx)
Usable security
Partners
Funding
Ethics
Augmented Science
Join HIIT
People & contact us

Statistical theory

We work on probabilistic statistical models for analyzing multivariate data. This is not only important for the neuroscientific applications, but also leads to general-purpose statistical models.

A fundamental mathematical method that we use is independent component analysis together with some of its extensions. A particularly important project is on causal analysis.

Research projects: FastICA, ICASSO, NMFsc, LiNGAM (causal analysis), Score matching


Last updated 23 Jan 2009 by Aapo Hyvärinen. Page created 13 Jan 2007 by Webmaster.