Simo Särkkä

Senior Researcher, Dr.Tech. (BECS)
Docent [∼Adj.Prof.] (TUT & LUT)

Postal Address:

P.O.Box 12200
FIN-00076 AALTO
FINLAND

Street Address:

Room F305, F-Talo, 3rd Floor
Rakentajanaukio 2
Espoo, Finland

Contact:

+358 50 512 4393
simo.sarkka(at)aalto.fi

Research Activities

  • Applications

    • Signal Processing and State Estimation in Brain Imaging (fMRI/MEG/EEG/DOT)
    • State Estimation in Inverse Problems and Kriging
    • Audio signal processing, location sensing, passive sensor based target tracking.

  • Bayesian Inference Methods for Stochastic Dynamic Systems

    • Non-Linear Kalman Filtering and Smoothing
    • Continuous-Time Stochastic Models and Stochastic Differential Equations (SDE)
    • Particle Filtering and Sequential Monte Carlo Methods

  • Bayesian Inference Methods for Spatial and Spatio-Temporal Systems

    • Gaussian Process Regression and Machine Learning
    • Stochastic Partial/Pseudo Differential Equations (SPDE)
    • Infinite-dimensional/distributed-parameter Kalman filtering

Publications

My Google Scholar profile: http://scholar.google.com/citations?user=QVhmc9cAAAAJ

See also Department's publication list.

The PDF preprints below are draft versions of the articles and they are here to give people an opportunity to check the relevance of the articles before purchasing the final articles from the publisher. Please send me an email if you want the latest preprints of the submitted articles.

Books

  1. Simo Särkkä (2013). Bayesian Filtering and Smoothing. Cambridge University Press. Forthcoming in August 2013. http://www.cambridge.org/us/knowledge/isbn/item7267681

Journals

  1. S. Särkkä, A. Solin, and J. Hartikainen (2013). Spatio-Temporal Learning via Infinite-Dimensional Bayesian Filtering and Smoothing. Accepted for publication in IEEE Signal Processing Magazine.
  2. S. Särkkä and J. Sarmavuori (2013). Gaussian Filtering and Smoothing for Continuous-Discrete Dynamic Systems. Signal Processing, Volume 93. Issue 2, Pages 500-510. (Preprint, DOI, Matlab toolbox)
  3. I. S. Mbalawata, S. Särkkä, and H. Haario (2013). Parameter Estimation in Stochastic Differential Equations with Markov Chain Monte Carlo and Non-Linear Kalman Filtering. Computational Statistics, in press. (DOI)
  4. S. Särkkä, A. Solin, A. Nummenmaa, A. Vehtari, T. Auranen, S. Vanni, F.-H. Lin (2012). Dynamic Retrospective Filtering of Physiological Noise in BOLD fMRI: DRIFTER. NeuroImage, Volume 60, Issue 2, Pages 1517-1527. (DOI, Preprint, Matlab toolbox)
  5. J. Sarmavuori and S. Särkkä (2012). Fourier-Hermite Kalman Filter. IEEE Transactions on Automatic Control, Volume 57, Issue 6, Pages 1511-1515. (DOI, Preprint)
  6. S. Särkkä, V. Viikari, M. Huusko, and K. Jaakkola (2012). Phase-Based UHF RFID Tracking with Non-Linear Kalman Filtering and Smoothing. IEEE Sensors Journal, Volume 12, Issue 5, Pages 904-910. (DOI, Preprint)
  7. S. Särkkä and A. Huovilainen (2011). Accurate Discretization of Analog Audio Filters with Application to Parametric Equalizer Design. IEEE Transactions on Audio, Speech, and Language Processing, Volume 19, Issue 8, Pages 2486-2493. (DOI , Preprint, Matlab code, C++ code, VST Effect for OS X)
  8. P. Hiltunen, S. Särkkä, I. Nissilä, A. Lajunen and J. Lampinen (2011). State space regularization in the nonstationary inverse problem for diffuse optical tomography. Inverse Problems, Volume 27, Number 2. (DOI)
  9. S. Särkkä and J. Hartikainen (2010). On Gaussian Optimal Smoothing of Non-Linear State Space Models. IEEE Transactions on Automatic Control, Volume 55, Issue 8, Pages 1938-1941. (DOI, Preprint, Matlab toolbox). See also errata DOI or Preprint.
  10. S. Särkkä (2010). Continuous-Time and Continuous-Discrete-Time Unscented Rauch-Tung-Striebel Smoothers. Signal Processing, Volume 90, Issue 1, Pages 225-235. (DOI, Preprint)
  11. S. Särkkä and A. Nummenmaa (2009). Recursive Noise Adaptive Kalman Filtering by Variational Bayesian Approximations. IEEE Transactions on Automatic Control, Volume 54, Issue 3, Pages 596-600. (DOI, Preprint, Matlab code)
  12. S. Särkkä and T. Sottinen (2008). Application of Girsanov Theorem to Particle Filtering of Discretely Observed Continuous-Time Non-Linear Systems. Bayesian Analysis, Volume 3, Number 03, Pages 555-584. (DOI)
  13. S. Särkkä (2008). Unscented Rauch-Tung-Striebel Smoother. IEEE Transactions on Automatic Control, Volume 53, Issue 3, Pages 845-849. (DOI, Preprint, Matlab toolbox)
  14. S. Särkkä, A. Vehtari, and J. Lampinen (2007). Rao-Blackwellized Particle Filter for Multiple Target Tracking. Information Fusion Journal, Volume 8, Issue 1, Pages 2-15. (DOI, Preprint, Matlab toolbox)
  15. S. Särkkä, A. Vehtari, and J. Lampinen (2007). CATS Benchmark Time Series Prediction by Kalman Smoother with Cross-Validated Noise Density. Neurocomputing, Volume 70, Issues 13-15, Pages 2331-2341. (DOI Preprint)
  16. S. Särkkä (2007). On Unscented Kalman Filtering for State Estimation of Continuous-Time Nonlinear Systems. IEEE Transactions on Automatic Control, Volume 52, Issue 9, Pages 1631-1641. (DOI, Preprint)

Conference Proceedings

  1. X. Chen, S. Särkkä, and S. Godsill (2013). Probabilistic Initiation and Termination for MEG Multiple Dipole Localization Using Sequential Monte Carlo Methods. Accepted for publication in Proceedings of FUSION 2013.
  2. S. Särkkä and A. Solin (2013). Continuous-Space Gaussian Process Regression and Generalized Wiener Filtering with Application to Learning Curves. Accepted for publication in Proceedings of SCIA 2013. (Preprint as PDF)
  3. A. Solin, E. Glerean, and S. Särkkä (2013). Time-Frequency Dynamics of Brain Connectivity by Stochastic Oscillator Models and Kalman Filtering. Accepted for publication in Proceedings of OHBM 2013 (abstract and poster).
  4. A. Solin, S. Särkkä, A. Nummenmaa, A. Vehtari, T. Auranen, S. Vanni, F.-H. Lin (2013). Volumetric Space-Time Structure of Physiological Noise in BOLD fMRI. Accepted for publication in Proceedings of ISMRM 2013 (abstract and poster).
  5. S.M.J. Lyons, A.J. Storkey, and S. Särkkä (2012). The Coloured Noise Expansion and Parameter Estimation of Diffusion Processes. Proceedings of NIPS, pages 1961-1969. (PDF)
  6. R. Piché, S. Särkkä and J. Hartikainen (2012). Recursive Outlier-Robust Filtering and Smoothing for Nonlinear Systems Using the Multivariate Student-t Distribution. In Proceedings of MLSP. (Preprint as PDF)
  7. J. Sarmavuori and S. Särkkä (2012). Fourier-Hermite Rauch-Tung-Striebel Smoother. Proceedings of EUSIPCO, pages 2109-2113. (Preprint as PDF)
  8. S. Särkkä, P. Bunch and S. J. Godsill (2012). A Backward-Simulation Based Rao-Blackwellized Particle Smoother for Conditionally Linear Gaussian Models. Proceedings of SYSID 2012, pages 506-511. (invited paper). (Preprint as PDF)
  9. S. Särkkä and A. Solin (2012). On Continuous-Discrete Cubature Kalman Filtering. Proceedings of SYSID 2012, pages 1210-1215. (Preprint)
  10. J. Hartikainen, M. Seppänen and S. Särkkä (2012). State-Space Inference for Non-Linear Latent Force Models with Application to Satellite Orbit Prediction. Proceedings of The 29th International Conference on Machine Learning (ICML 2012). (PDF)
  11. S. Särkkä and J. Hartikainen (2012). Infinite-Dimensional Kalman Filtering Approach to Spatio-Temporal Gaussian Process Regression. JMLR Workshop and Conference Proceedings Volume 22: AISTATS 2012, Pages 993-1001. (Preprint)
  12. S. Särkkä, A. Solin, A. Nummenmaa, A. Vehtari, T. Auranen, S. Vanni and F.-H. Lin (2012). Identification of Spatio-Temporal Oscillatory Signal Structure in Cerebral Hemodynamics Using DRIFTER. Proceedings of ISMRM 2012. (E-Poster, Abstract)
  13. J. Hartikainen and S. Särkkä (2011). Sequential Inference for Latent Force Models. Proceedings of The 27th Conference on Uncertainty in Artificial Intelligence (UAI 2011) (Preprint)
  14. J. Hartikainen, J. Riihimäki and S. Särkkä (2011). Sparse Spatio-Temporal Gaussian Processes with General Likelihoods. Proceedings of International Conference on Artificial Neural Networks (ICANN) (DOI, Preprint)
  15. S. Särkkä (2011). Linear Operators and Stochastic Partial Differential Equations in Gaussian Process Regression. Proceedings of International Conference on Artificial Neural Networks (ICANN) (DOI, Preprint)
  16. S. Särkkä (2011). Learning Curves for Gaussian Processes via Numerical Cubature Integration. Proceedings of International Conference on Artificial Neural Networks (ICANN) (DOI, Preprint)
  17. S. Särkkä, A. Nummenmaa, A. Solin, A. Vehtari, T. Witzel, T. Auranen, S. Vanni, M.S. Hämäläinen, and F-H. Lin. Dynamical statistical modeling of physiological noise for fast BOLD fMRI. Proceedings of ISMRM 2011. (E-Poster)
  18. J. Hartikainen and S. Särkkä (2010). Kalman Filtering and Smoothing Solutions to Temporal Gaussian Process Regression Models. Proceedings of IEEE International Workshop on Machine Learning for Signal Processing (MLSP) (Preprint)
  19. S. Särkkä and J. Hartikainen (2010). Sigma Point Methods in Optimal Smoothing of Non-Linear Stochastic State Space Models. Proceedings of IEEE International Workshop on Machine Learning for Signal Processing (MLSP) (Preprint)
  20. S. Särkkä, A. Vehtari, and J. Lampinen (2007). Prediction of ESTSP Competition Time Series by Unscented Kalman Filter and RTS Smoother. Proceedings of ESTSP 2007 (Preprint)
  21. S. Särkkä (2006). On Sequential Monte Carlo Sampling of Discretely Observed Stochastic Differential Equations. Proceedings of NSSPW, (Preprint)
  22. S. Särkkä, A. Vehtari, and J. Lampinen (2004). Time series prediction by Kalman smoother with cross validated noise density. Proceedings of IJCNN 2004. The Winner of Time Series Prediction Competition - The CATS Benchmark (Preprint)
  23. S. Särkkä, A. Vehtari, and J. Lampinen (2004). Rao-Blackwellized Monte Carlo data association for multiple target tracking. Proceedings of FUSION 2004 (Preprint, Matlab toolbox)
  24. A. Vehtari, S. Särkkä, and J. Lampinen (2000). On MCMC sampling in Bayesian MLP neural networks. Proceedings of the IJCNN 2000 (Preprint as ps.gz)

Doctoral Dissertation

  1. S. Särkkä (2006). Recursive Bayesian Inference on Stochastic Differential Equations. Doctoral dissertation, Helsinki University of Technology (Thesis as PDF)

Technical Reports

  1. A. Solin and S. Särkkä (2013). Infinite-Dimensional Bayesian Filtering for Detection of Quasi-Periodic Phenomena in Spatio-Temporal Data. (arXiv)
  2. S.M.J. Lyons, S. Särkkä, and A.J. Storkey (2013). Series Expansion Approximations of Brownian Motion for Non-Linear Kalman Filtering of Diffusion Processes. (arXiv)
  3. S. Särkkä and J. Hartikainen (2013). Variational Bayesian Adaptation of Noise Covariances in Non-Linear Kalman Filtering. (arXiv)
  4. S. Särkkä (2007). Notes on Quaternions. Technical report. (Report as PDF)
  5. S. Särkkä, Toni Tamminen, Aki Vehtari, and Jouko Lampinen (2004). Probabilistic methods in multiple target tracking - Review and bibliography. Technical report B36, ISBN 951-22-6938-4, Helsinki University of Technology. Laboratory of Computational Engineering (Report as PDF)
  6. S. Särkkä (2000). Bayesilaiset menetelmät audiovisuaalisen puheen havaitsemisen mallintamisessa. Diploma thesis, (in Finnish) (Thesis as ps.gz)
  7. S. Särkkä (1999). MCMC-menetelmät ja diagnostiikat. Technical report (in Finnish). (HTML, ps.gz)

Course material:

  1. S. Särkkä (2012). Applied Stochastic Differential Equations. Lecture notes of the course MAT-55216 Topics in Applied Mathematics held in Autumn 2012. (Booklet as PDF, Slides and exercises).
  2. S. Särkkä (2012). Bayesian Estimation of Time-Varying Systems: Discrete-Time Systems. Lectures notes of the course S-114.4610 held in Spring 2012 (Booklet as PDF, Slides and Exercises). (2011 material is here). Planned to be published as book by Cambridge University Press in 2013.

Patents

  1. WO/2004/111677
  2. WO/2008/034944
  3. WO/2006/108921

Submitted

  1. S. Särkkä, J. Hartikainen, I. S. Mbalawata, H. Haario. Posterior Inference on Parameters of Stochastic Differential Equations via Gaussian Process Approximations and Adaptive MCMC. Submitted.
  2. A. Solin and S. Särkkä. Infinite-Dimensional Bayesian Filtering for Detection of Quasi-Periodic Phenomena in Spatio-Temporal Data. Submitted.
  3. S.M.J. Lyons, S. Särkkä, and A.J. Storkey. Series Expansion Approximations of Brownian Motion for Non-Linear Kalman Filtering of Diffusion Processes. Submitted.

Software and Audio

Software Packages

Some Matlab toolboxes where I have contributed to (see also the code examples linked in the publication list above):

Audio Signal Generation Projects

Teaching

Some courses etc. that I am giving / have given / will give soon: