Mika Sipilä

Doctoral Researcher

Unit

Faculty of Mathematics and Science

Department / Division

Department of Mathematics and Statistics

Room number

MaD 319

mika.e.sipila@jyu.fi

Postal address

Ahlmaninkatu 2

Publications

Publication

2025

Identifiable Autoregressive Variational Autoencoders for Nonlinear and Nonstationary Spatio-Temporal Blind Source Separation

Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Lecture Notes in Computer Science. Springer Nature Switzerland.

Sipilä, Mika

Nordhausen, Klaus

Taskinen, Sara

Publication

2025

Modelling multivariate spatio-temporal data with identifiable variational autoencoders

Neural Networks.

Sipilä, Mika

Cappello, Claudia

De Iaco, Sandra

Nordhausen, Klaus

Taskinen, Sara

Publication

2024

Nonlinear blind source separation exploiting spatial nonstationarity

Information Sciences.

Sipilä, Mika

Nordhausen, Klaus

Taskinen, Sara

Publication

2024

Robust second-order stationary spatial blind source separation using generalized sign matrices

Spatial Statistics.

Sipilä, Mika

Muehlmann, Christoph

Nordhausen, Klaus

Taskinen, Sara

Publication

2022

SpatialBSS : Blind Source Separation for Multivariate Spatial Data

CRAN - The Comprehensive R Archive Network.

Muehlmann, Christoph

Sipilä, Mika

Nordhausen, Klaus

Taskinen, Sara

Virta, Joni

Mika Sipilä

Identifiable Autoregressive Variational Autoencoders for Nonlinear and Nonstationary Spatio-Temporal Blind Source Separation

Modelling multivariate spatio-temporal data with identifiable variational autoencoders

Nonlinear blind source separation exploiting spatial nonstationarity

Robust second-order stationary spatial blind source separation using generalized sign matrices

SpatialBSS : Blind Source Separation for Multivariate Spatial Data

Multivariate statistics