Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Simo Särkkä

System identification using Bayesian neural networks with nonparametric noise models


Apr 25, 2021
Christos Merkatas, Simo Särkkä

* Submitted to Statistics and Computing 

  Access Paper or Ask Questions

Gaussian Process Regression in Logarithmic Time


Mar 10, 2021
Adrien Corenflos, Zheng Zhao, Simo Särkkä

* 9 pages, 3 figures, 2 tables. Supplementary can be found in Ancilliary files 

  Access Paper or Ask Questions

Temporal Parallelization of Inference in Hidden Markov Models


Feb 10, 2021
Sakira Hassan, Simo Särkkä, Ángel F. García-Fernández

* submitted to the IEEE transactions on Signal Processing 

  Access Paper or Ask Questions

A Probabilistic Taylor Expansion with Applications in Filtering and Differential Equations


Feb 01, 2021
Toni Karvonen, Jon Cockayne, Filip Tronarp, Simo Särkkä


  Access Paper or Ask Questions

Deep State-Space Gaussian Processes


Aug 11, 2020
Zheng Zhao, Muhammad Emzir, Simo Särkkä

* Submitted to Statistics and Computing. The code will be revealed at https://github.com/zgbkdlm/SS-DGP upon acceptance 

  Access Paper or Ask Questions

Continuous-Discrete Filtering and Smoothing on Submanifolds of Euclidean Space


Apr 17, 2020
Filip Tronarp, Simo Särkkä


  Access Paper or Ask Questions

Maximum likelihood estimation and uncertainty quantification for Gaussian process approximation of deterministic functions


Feb 24, 2020
Toni Karvonen, George Wynne, Filip Tronarp, Chris J. Oates, Simo Särkkä

* Fixed some small errors and included a few references 

  Access Paper or Ask Questions

Taylor Moment Expansion for Continuous-Discrete Gaussian Filtering and Smoothing


Jan 08, 2020
Zheng Zhao, Toni Karvonen, Roland Hostettler, Simo Särkkä

* Submitted to IEEE Transactions on Automatic Control. Code is available at (once accepted for publication) https://github.com/zgbkdlm/TME-filter-smoother 

  Access Paper or Ask Questions

Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals using Feature Engineering and a Bidirectional LSTM Network


Sep 06, 2019
Ali Bahrami Rad, Morteza Zabihi, Zheng Zhao, Moncef Gabbouj, Aggelos K. Katsaggelos, Simo Särkkä


  Access Paper or Ask Questions

The Use of Gaussian Processes in System Identification


Jul 13, 2019
Simo Särkkä

* To appear in Encyclopedia of systems and control, 2nd edition 

  Access Paper or Ask Questions

1D Convolutional Neural Network Models for Sleep Arousal Detection


Mar 01, 2019
Morteza Zabihi, Ali Bahrami Rad, Serkan Kiranyaz, Simo Särkkä, Moncef Gabbouj

* 10 pages, 6 figures 

  Access Paper or Ask Questions

Kalman-based Spectro-Temporal ECG Analysis using Deep Convolutional Networks for Atrial Fibrillation Detection


Dec 12, 2018
Zheng Zhao, Simo Särkkä, Ali Bahrami Rad

* 13 pages 

  Access Paper or Ask Questions

Improved Calibration of Numerical Integration Error in Sigma-Point Filters


Nov 28, 2018
Jakub Prüher, Toni Karvonen, Chris J. Oates, Ondřej Straka, Simo Särkkä

* 13 pages, 4 figures 

  Access Paper or Ask Questions

LSD$_2$ - Joint Denoising and Deblurring of Short and Long Exposure Images with Convolutional Neural Networks


Nov 23, 2018
Janne Mustaniemi, Juho Kannala, Jiri Matas, Simo Särkkä, Janne Heikkilä


  Access Paper or Ask Questions

Probabilistic Solutions To Ordinary Differential Equations As Non-Linear Bayesian Filtering: A New Perspective


Oct 08, 2018
Filip Tronarp, Hans Kersting, Simo Särkkä, Philipp Hennig


  Access Paper or Ask Questions

Inertial-aided Motion Deblurring with Deep Networks


Oct 01, 2018
Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä


  Access Paper or Ask Questions

Gaussian process classification using posterior linearisation


Sep 13, 2018
Ángel F. García-Fernández, Filip Tronarp, Simo Särkkä


  Access Paper or Ask Questions

Probabilistic approach to limited-data computed tomography reconstruction


Sep 11, 2018
Zenith Purisha, Carl Jidling, Niklas Wahlström, Simo Särkkä, Thomas B. Schön


  Access Paper or Ask Questions

Gaussian Process Latent Force Models for Learning and Stochastic Control of Physical Systems


Aug 13, 2018
Simo Särkkä, Mauricio A. Álvarez, Neil D. Lawrence


  Access Paper or Ask Questions

Hilbert Space Methods for Reduced-Rank Gaussian Process Regression


Jun 07, 2018
Arno Solin, Simo Särkkä


  Access Paper or Ask Questions

Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements


May 22, 2018
Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä


  Access Paper or Ask Questions

Modeling and interpolation of the ambient magnetic field by Gaussian processes


Mar 21, 2018
Arno Solin, Manon Kok, Niklas Wahlström, Thomas B. Schön, Simo Särkkä

* 17 pages, 12 figures, to appear in IEEE Transactions on Robotics 

  Access Paper or Ask Questions

Parallelizable sparse inverse formulation Gaussian processes (SpInGP)


Sep 28, 2017
Alexander Grigorievskiy, Neil Lawrence, Simo Särkkä

* Presented at Machine Learning in Signal Processing (MLSP2017) 

  Access Paper or Ask Questions

Inertial-Based Scale Estimation for Structure from Motion on Mobile Devices


Aug 11, 2017
Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä


  Access Paper or Ask Questions

A probabilistic model for the numerical solution of initial value problems


Aug 10, 2017
Michael Schober, Simo Särkkä, Philipp Hennig

* 23 pages, 11 figures 

  Access Paper or Ask Questions

Student-t Process Quadratures for Filtering of Non-Linear Systems with Heavy-Tailed Noise


Mar 16, 2017
Jakub Prüher, Filip Tronarp, Toni Karvonen, Simo Särkkä, Ondřej Straka

* 15 pages, 3 figures, submitted to 20th International Conference on Information Fusion, 2017 

  Access Paper or Ask Questions

Regularizing Solutions to the MEG Inverse Problem Using Space-Time Separable Covariance Functions


Apr 17, 2016
Arno Solin, Pasi Jylänki, Jaakko Kauramäki, Tom Heskes, Marcel A. J. van Gerven, Simo Särkkä

* 25 pages, 7 figures 

  Access Paper or Ask Questions

Computationally Efficient Bayesian Learning of Gaussian Process State Space Models


Apr 15, 2016
Andreas Svensson, Arno Solin, Simo Särkkä, Thomas B. Schön


  Access Paper or Ask Questions