Thomas Schön
Professor i artificiell intelligens vid Institutionen för informationsteknologi; Systemteknik
- Telefon:
- 018-471 25 94
- Mobiltelefon:
- 073-593 38 87
- E-post:
- thomas.schon@it.uu.se
- Besöksadress:
- Hus 10, Regementsvägen 10
- Postadress:
- Box 337
751 05 UPPSALA
- Akademiska meriter:
- Docent
Kort presentation
Thomas B. Schön är Beijerprofessor i artificiell intelligens vid institutionen för informationsteknologi vid Uppsala universitet och vetenskaplig ledare för det femåriga projektet AI4Research. Han doktorerade i reglerteknik i februari 2006 vid Linköpings universitet, och har tidigare varit verksam vid University of Cambridge (Storbritannien), University of Newcastle (Australien) och Técnica Federico Santa María (Valparaíso, Chile).
Nyckelord
- artificial intelligence
- machine learning
- automatic control
- deep learning
- signal processing
- computer vision
- data analytics
- decision-making with algorithms
- artificiell intelligens
- maskininlärning
- ai4research
- reglerteknik
- signalbehandling
- datorseende
Biografi
Thomas B. Schön är Beijerprofessor i artificiell intelligens vid institutionen för informationsteknologi vid Uppsala universitet och vetenskaplig ledare för det femåriga projektet AI4Research. Han doktorerade i reglerteknik i februari 2006, tog sin Masterexamen i tillämpad fysik och elektroteknik i september 2001 och sin kandidatexamen i företagsekonomi 2001, samtliga vid Linköpings universitet. Han har tidigare varit verksam vid University of Cambridge (Storbritannien), University of Newcastle (Australien) och Técnica Federico Santa María (Valparaíso, Chile). 2018 valdes han in i Kungl. Ingenjörsvetenskapsakademien och Kungliga Vetenskaps-Societeten (Uppsala). Han belönades med Tage Erlanders pris i naturvetenskap och teknik 2017 och Arnbergska priset 2016, som båda utdelas av Kungl. Vetenskapsakademien. Han belönades år 2014 med Automatica Best Paper Prize och 2013 med Best PhD Thesis Award av the European Association for Signal Processing 2009 utsågs han till bästa lärare vid Linköpings universitets tekniska högskola. Han är medlem i IEEE (Institute of Electrical and Electronics Engineers) och i ELLIS Society.
Thomas Schön har ett brett intresse för att utveckla nya algoritmer och matematiska modeller som kan lära sig och agera utifrån data. Hans huvudsakliga vetenskapliga fält är maskininlärning, men han publicerar regelbundet inom andra fält såsom statistik, reglerteknik, signalbehandling och datorseende. Han bedriver både grundforskning och tillämpad forskning, där det sistnämnda oftast genomförs i samarbete med industri eller tillämpade forskargrupper.

Publikationer
Senaste publikationer
-
Is supervised learning really that different from un-supervised?
2026
-
Learning dynamics from input-output data with Hamiltonian Gaussian processes.
2026
-
Towards safe control parameter tuning in distributed multi-agent systems
Ingår i 2025 IEEE 64th Conference on Decision and Control (CDC), 2025
-
PACSBO: Probably Approximately Correct Safe Bayesian Optimization
Ingår i Systems Theory in Data and Optimization, s. 3-18, 2025
-
Reinforcement learning with non-ergodic reward increments: robustness via ergodicity transformations
Ingår i Transactions on Machine Learning Research, 2025
Alla publikationer
Artiklar i tidskrift
-
Reinforcement learning with non-ergodic reward increments: robustness via ergodicity transformations
Ingår i Transactions on Machine Learning Research, 2025
-
Safe Bayesian Optimization Across Noise Models via Scenario Programming
Ingår i IEEE Control Systems Letters, s. 3029-3034, 2025
-
Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization
Ingår i Advances Neural Information Processing Systems, 2025
-
Automated segmentation of synchrotron-scanned fossils
Ingår i Fossil Record, s. 103-114, 2025
- DOI för Automated segmentation of synchrotron-scanned fossils
- Ladda ner fulltext (pdf) av Automated segmentation of synchrotron-scanned fossils
-
Conditional sampling within generative diffusion models
Ingår i Philosophical Transactions. Series A, 2025
- DOI för Conditional sampling within generative diffusion models
- Ladda ner fulltext (pdf) av Conditional sampling within generative diffusion models
-
Deep networks for system identification: A survey
Ingår i Automatica, 2025
- DOI för Deep networks for system identification: A survey
- Ladda ner fulltext (pdf) av Deep networks for system identification: A survey
-
Ingår i Computers in Cardiology (CinC), 2024
-
Uncertainty Estimation with Recursive Feature Machines
Ingår i Proceedings of Machine Learning Research, s. 1408-1437, 2024
-
Ingår i IFAC-PapersOnLine, s. 247-252, 2024
-
Ingår i Neurocritical Care, s. 387-397, 2024
- DOI för Machine Learning Based Prediction of Imminent ICP Insults During Neurocritical Care of Traumatic Brain Injury
- Ladda ner fulltext (pdf) av Machine Learning Based Prediction of Imminent ICP Insults During Neurocritical Care of Traumatic Brain Injury
-
Rao-Blackwellized particle smoothing for simultaneous localization and mapping
Ingår i DATA-CENTRIC ENGINEERING, 2024
- DOI för Rao-Blackwellized particle smoothing for simultaneous localization and mapping
- Ladda ner fulltext (pdf) av Rao-Blackwellized particle smoothing for simultaneous localization and mapping
-
On the Equivalence of Direct and Indirect Data-Driven Predictive Control Approaches
Ingår i IEEE Control Systems Letters, s. 796-801, 2024
-
Evaluating regression and probabilistic methods for ECG-based electrolyte prediction
Ingår i Scientific Reports, 2024
- DOI för Evaluating regression and probabilistic methods for ECG-based electrolyte prediction
- Ladda ner fulltext (pdf) av Evaluating regression and probabilistic methods for ECG-based electrolyte prediction
-
Safe Reinforcement Learning in Uncertain Contexts
Ingår i IEEE Transactions on robotics, s. 1828-1841, 2024
-
Late Breaking Abstract - automated cough analysis: The value of own data vs open sound databases
Ingår i European Respiratory Journal, 2023
-
Smoothed State Estimation via Efficient Solution of Linear Equations
Ingår i IEEE Transactions on Automatic Control, s. 5877-5889, 2023
-
Variational Elliptical Processes
Ingår i Transactions on Machine Learning Research, 2023
-
How Reliable is Your Regression Model’s Uncertainty Under Real-World Distribution Shifts?
Ingår i Transactions on Machine Learning Research, 2023
-
Online Learning for Prediction via Covariance Fitting: Computation, Performance and Robustness
Ingår i Transactions on Machine Learning Research, 2023
-
Gaussian inference for data-driven state-feedback design of nonlinear systems
Ingår i IFAC-PapersOnLine, s. 4796-4803, 2023
- DOI för Gaussian inference for data-driven state-feedback design of nonlinear systems
- Ladda ner fulltext (pdf) av Gaussian inference for data-driven state-feedback design of nonlinear systems
-
Neural motion planning in dynamic environments
Ingår i IFAC-PapersOnLine, s. 10126-10131, 2023
- DOI för Neural motion planning in dynamic environments
- Ladda ner fulltext (pdf) av Neural motion planning in dynamic environments
-
On the regularization in DeePC
Ingår i IFAC-PapersOnLine, s. 625-631, 2023
-
On the trade-off between event-based and periodic state estimation under bandwidth constraints
Ingår i IFAC-PapersOnLine, s. 5275-5280, 2023
- DOI för On the trade-off between event-based and periodic state estimation under bandwidth constraints
- Ladda ner fulltext (pdf) av On the trade-off between event-based and periodic state estimation under bandwidth constraints
-
Variational Elliptical Processes
Ingår i Transactions on Machine Learning Research, 2023
-
Screening for Chagas disease from the electrocardiogram using a deep neural network
Ingår i PLoS Neglected Tropical Diseases, 2023
- DOI för Screening for Chagas disease from the electrocardiogram using a deep neural network
- Ladda ner fulltext (pdf) av Screening for Chagas disease from the electrocardiogram using a deep neural network
-
How Reliable is Your Regression Model’s Uncertainty Under Real-World Distribution Shifts?
Ingår i Transactions on Machine Learning Research, 2023
-
Invertible Kernel PCA With Random Fourier Features
Ingår i IEEE Signal Processing Letters, s. 563-567, 2023
-
Ingår i Computer Methods in Applied Mechanics and Engineering, 2023
- DOI för Inferring the probability distribution over strain tensors in polycrystals from diffraction based measurements
- Ladda ner fulltext (pdf) av Inferring the probability distribution over strain tensors in polycrystals from diffraction based measurements
-
Smoothed State Estimation via Efficient Solution of Linear Equations
Ingår i IEEE Transactions on Automatic Control, s. 5877-5889, 2023
-
Overparameterized Linear Regression Under Adversarial Attacks
Ingår i IEEE Transactions on Signal Processing, s. 601-614, 2023
-
Variational system identification for nonlinear state-space models
Ingår i Automatica, 2023
-
Probabilistic Estimation of Instantaneous Frequencies of Chirp Signals
Ingår i IEEE Transactions on Signal Processing, s. 461-476, 2023
-
Artificiell intelligens för kardiologer
Ingår i Svensk kardiologi, s. 20-25, 2022
-
Incorporating Sum Constraints into Multitask Gaussian Processes
Ingår i Transactions on Machine Learning Research, s. 1-28, 2022
-
Predicting Political Violence Using a State-Space Model
Ingår i International Interactions, s. 759-777, 2022
-
Ingår i Scientific Reports, 2022
- DOI för Development and validation of deep learning ECG-based prediction of myocardial infarction in emergency department patients
- Ladda ner fulltext (pdf) av Development and validation of deep learning ECG-based prediction of myocardial infarction in emergency department patients
-
Ingår i IEEE Transactions on Signal Processing, s. 3676-3692, 2022
-
Ingår i IEEE CONTROL SYSTEMS MAGAZINE, s. 75-102, 2022
-
Data to Controller for Nonlinear Systems: An Approximate Solution
Ingår i IEEE Control Systems Letters, s. 1196-1201, 2022
-
Ingår i IEEE Transactions on Visualization and Computer Graphics, s. 2602-2614, 2022
-
Memory efficient constrained optimization of scanning-beam lithography
Ingår i Optics Express, s. 20564-20579, 2022
- DOI för Memory efficient constrained optimization of scanning-beam lithography
- Ladda ner fulltext (pdf) av Memory efficient constrained optimization of scanning-beam lithography
-
ResNet-based ECG Diagnosis of Myocardial Infarction in the Emergency Department
Ingår i Machine learning from ground truth: New medical imaging datasets for unsolved medical problems Workshop at NeurIPS, 2021
-
Deep neural network-estimated electrocardiographic age as a mortality predictor
Ingår i Nature Communications, 2021
- DOI för Deep neural network-estimated electrocardiographic age as a mortality predictor
- Ladda ner fulltext (pdf) av Deep neural network-estimated electrocardiographic age as a mortality predictor
-
Stochastic quasi-Newton with line-search regularisation
Ingår i Automatica, 2021
-
Gaussian Variational State Estimation for Nonlinear State-Space Models
Ingår i IEEE Transactions on Signal Processing, s. 5979-5993, 2021
-
Quantifying the Uncertainty of the Relative Geometry in Inertial Sensors Arrays
Ingår i IEEE Sensors Journal, s. 19362-19373, 2021
- DOI för Quantifying the Uncertainty of the Relative Geometry in Inertial Sensors Arrays
- Ladda ner fulltext (pdf) av Quantifying the Uncertainty of the Relative Geometry in Inertial Sensors Arrays
-
Universal probabilistic programming offers a powerful approach to statistical phylogenetics
Ingår i Communications Biology, 2021
- DOI för Universal probabilistic programming offers a powerful approach to statistical phylogenetics
- Ladda ner fulltext (pdf) av Universal probabilistic programming offers a powerful approach to statistical phylogenetics
-
Machine Learning in Risk Prediction
Ingår i Hypertension, s. 1165-1166, 2020
-
Automatic diagnosis of the 12-lead ECG using a deep neural network
Ingår i Nature Communications, 2020
- DOI för Automatic diagnosis of the 12-lead ECG using a deep neural network
- Ladda ner fulltext (pdf) av Automatic diagnosis of the 12-lead ECG using a deep neural network
-
Nonlinear Input Design as Optimal Control of a Hamiltonian System
Ingår i IEEE Control Systems Letters, s. 85-90, 2020
-
Learning Robust LQ-Controllers Using Application Oriented Exploration
Ingår i IEEE Control Systems Letters, s. 19-24, 2020
-
The effect of interventions on COVID-19
Ingår i Nature, 2020
-
On the smoothness of nonlinear system identification
Ingår i Automatica, 2020
-
Smoothing With Couplings of Conditional Particle Filters
Ingår i Journal of the American Statistical Association, s. 721-729, 2020
-
Getting started with particle Metropolis-Hastings for inference in nonlinear dynamical models
Ingår i Journal of Statistical Software, s. 1-41, 2019
- DOI för Getting started with particle Metropolis-Hastings for inference in nonlinear dynamical models
- Ladda ner fulltext (pdf) av Getting started with particle Metropolis-Hastings for inference in nonlinear dynamical models
-
Data Consistency Approach to Model Validation
Ingår i IEEE Access, s. 59788-59796, 2019
- DOI för Data Consistency Approach to Model Validation
- Ladda ner fulltext (pdf) av Data Consistency Approach to Model Validation
-
Identification of a Duffing oscillator using particle Gibbs with ancestor sampling
Ingår i Journal of Physics, Conference Series, 2019
- DOI för Identification of a Duffing oscillator using particle Gibbs with ancestor sampling
- Ladda ner fulltext (pdf) av Identification of a Duffing oscillator using particle Gibbs with ancestor sampling
-
Probabilistic approach to limited-data computed tomography reconstruction
Ingår i Inverse Problems, 2019
-
A Fast and Robust Algorithm for Orientation Estimation Using Inertial Sensors
Ingår i IEEE Signal Processing Letters, s. 1673-1677, 2019
-
Elements of Sequential Monte Carlo
Ingår i FOUNDATIONS AND TRENDS IN MACHINE LEARNING, s. 187-306, 2019
-
Neutron transmission strain tomography for non-constant stress-free lattice spacing
Ingår i Nuclear Instruments and Methods in Physics Research Section B, s. 64-73, 2019
-
High-Dimensional Filtering Using Nested Sequential Monte Carlo
Ingår i IEEE Transactions on Signal Processing, s. 4177-4188, 2019
-
On model order priors for Bayesian identification of SISO linear systems
Ingår i International Journal of Control, s. 1645-1661, 2019
-
Optimal controller/observer gains of discounted-cost LQG systems
Ingår i Automatica, s. 471-474, 2019
-
Ingår i Mechanical systems and signal processing, s. 915-928, 2018
-
Probabilistic learning of nonlinear dynamical systems using sequential Monte Carlo
Ingår i Mechanical systems and signal processing, s. 866-883, 2018
-
Probabilistic modelling and reconstruction of strain
Ingår i Nuclear Instruments and Methods in Physics Research Section B, s. 141-155, 2018
-
Automated learning with a probabilistic programming language: Birch
Ingår i Annual Reviews in Control, s. 29-43, 2018
-
Maximum likelihood identification of stable linear dynamical systems
Ingår i Automatica, s. 280-292, 2018
-
Modeling and Interpolation of the Ambient Magnetic Field by Gaussian Processes
Ingår i IEEE Transactions on robotics, s. 1112-1127, 2018
-
Smoothed State Estimation via Efficient Solution of Linear Equations
Ingår i IFAC-PapersOnLine, s. 1613-1618, 2017
-
System identification through online sparse Gaussian process regression with input noise
Ingår i IFAC Journal of Systems and Control, s. 1-11, 2017
-
Divide-and-Conquer with sequential Monte Carlo
Ingår i Journal of Computational And Graphical Statistics, s. 445-458, 2017
-
A flexible state–space model for learning nonlinear dynamical systems
Ingår i Automatica, s. 189-199, 2017
-
On robust input design for nonlinear dynamical models
Ingår i Automatica, s. 268-278, 2017
-
Rao–Blackwellized particle smoothers for conditionally linear Gaussian models
Ingår i IEEE Journal on Selected Topics in Signal Processing, s. 353-365, 2016
-
Using convolution to estimate the score function for intractable state-transition models
Ingår i IEEE Signal Processing Letters, s. 498-501, 2016
-
Mean and variance of the LQG cost function
Ingår i Automatica, s. 216-223, 2016
-
Magnetometer calibration using inertial sensors
Ingår i IEEE Sensors Journal, s. 5679-5689, 2016
-
A new structure exploiting derivation of recursive direct weight optimization
Ingår i IEEE Transactions on Automatic Control, s. 1683-1685, 2015
-
Indoor positioning using ultrawideband and inertial measurements
Ingår i IEEE Transactions on Vehicular Technology, s. 1293-1303, 2015
-
On the exponential convergence of the Kaczmarz algorithm
Ingår i IEEE Signal Processing Letters, s. 1571-1574, 2015
-
Particle Metropolis–Hastings using gradient and Hessian information
Ingår i Statistics and computing, s. 81-92, 2015
-
Particle Gibbs with ancestor sampling
Ingår i Journal of machine learning research, s. 2145-2184, 2014
Artiklar, forskningsöversikt
-
Taming diffusion models for image restoration: a review
Ingår i Philosophical Transactions. Series A, 2025
- DOI för Taming diffusion models for image restoration: a review
- Ladda ner fulltext (pdf) av Taming diffusion models for image restoration: a review
-
Guarantees for data-driven control of nonlinear systems using semidefinite programming: A survey
Ingår i Annual Reviews in Control, 2023
-
Sequential Monte Carlo: A Unified Review
Ingår i ANNUAL REVIEW OF CONTROL ROBOTICS AND AUTONOMOUS SYSTEMS, s. 159-182, 2023
- DOI för Sequential Monte Carlo: A Unified Review
- Ladda ner fulltext (pdf) av Sequential Monte Carlo: A Unified Review
Böcker
-
Machine learning: a first course for engineers and scientists
Cambridge University Press, 2022
-
Using Inertial Sensors for Position and Orientation Estimation
Now Publishers Inc., 2017
Konferensbidrag
-
Is supervised learning really that different from un-supervised?
2026
-
Learning dynamics from input-output data with Hamiltonian Gaussian processes.
2026
-
Towards safe control parameter tuning in distributed multi-agent systems
Ingår i 2025 IEEE 64th Conference on Decision and Control (CDC), 2025
-
PACSBO: Probably Approximately Correct Safe Bayesian Optimization
Ingår i Systems Theory in Data and Optimization, s. 3-18, 2025
-
Efficient Optimization Algorithms for Linear Adversarial Training
Ingår i International Conference on Artificial Intelligence and Statistics, s. 1207-1215, 2025
-
Safe exploration in reproducing kernel Hilbert spaces
Ingår i International Conference on Artificial Intelligence and Statistics, 2025
-
Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Models
Ingår i Proceedings of the 6th Northern Lights Deep Learning Conference (NLDL), s. 1-15, 2025
-
Conditioning diffusion models by explicit forward-backward bridging
Ingår i Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, s. 3709-3717, 2025
-
Meta-state-space identification of stochastic hearts
Ingår i Book of Abstracts 43rd Benelux Meeting on Systems and Control, s. 230-230, 2024
-
Non-ergodicity in reinforcement learning: robustness via ergodicity transformations
2024
-
Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
Ingår i 38th Conference on Neural Information Processing Systems, NeurIPS 2024, 2024
-
On Feynman–Kac training of partial Bayesian neural networks
Ingår i Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS), s. 3223-3231, 2024
-
Controlling Vision-Language Models for Multi-Task Image Restoration
Ingår i International Conference on Learning Representations 2024 (ICLR 2024), 2024
-
No Double Descent in Principal Component Regression: A High-Dimensional Analysis
Ingår i International Conference on Machine Learning (ICML), s. 15271-15293, 2024
-
Learning state observers for recurrent neural network models
Ingår i 2024 IEEE 63rd Conference on Decision and Control (CDC), s. 7871-7877, 2024
-
NTIRE 2024 restore any image model (RAIM) in the wild challenge
Ingår i 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops CVPRW 2024, s. 6632-6640, 2024
-
Entropy-regularized diffusion policy with Q-ensembles for offline reinforcement learning
Ingår i Advances in Neural Information Processing Systems 37 (NeurIPS 2024), 2024
-
Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models
Ingår i 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops CVPRW 2024, s. 6641-6651, 2024
-
A Model Predictive Control Approach to Motion Planning in Dynamic Environments
Ingår i 2024 European Control Conference (ECC), s. 3247-3254, 2024
-
Online Learning in Motion Modeling for Intra-interventional Image Sequences
Ingår i Medical Image Computing and Computer Assisted Intervention – MICCAI 2024, s. 706-716, 2024
- DOI för Online Learning in Motion Modeling for Intra-interventional Image Sequences
- Ladda ner fulltext (pdf) av Online Learning in Motion Modeling for Intra-interventional Image Sequences
-
Uncertainty Estimation with Recursive Feature Machines
2024
-
On feature learning of recursive feature machines and automatic relevance determination
2023
-
Regularization properties of adversarially-trained linear regression
Ingår i Advances in Neural Information Processing Systems 36 (NeurIPS 2023), s. 23658-23670, 2023
-
Image Restoration with Mean-Reverting Stochastic Differential Equations
Ingår i Proceedings of the 40th International Conference on Machine Learning, s. 23045-23066, 2023
-
NTIRE 2023 Image Shadow Removal Challenge Report
Ingår i 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), s. 1788-1807, 2023
-
Lens-to-Lens Bokeh Effect Transformation: NTIRE 2023 Challenge Report
Ingår i 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, s. 1643-1659, 2023
-
Refusion: Enabling Large-Size Realistic Image Restoration With Latent-Space Diffusion Models
Ingår i 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), s. 1680-1691, 2023
-
NTIRE 2023 HR NonHomogeneous Dehazing Challenge Report
Ingår i 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023
-
NTIRE 2023 Challenge on Stereo Image Super-Resolution: Methods and Results
Ingår i IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), s. 1346-1372, 2023
-
Unsupervised dynamic modeling of medical image transformations
Ingår i 2022 25th International Conference on Information Fusion (FUSION 2022), s. 1-7, 2022
-
Learning Proposals for Practical Energy-Based Regression
Ingår i International conference on artificial intelligence and statistics, vol 151, s. 4685-4704, 2022
-
Learning a Deformable Registration Pyramid
Ingår i Segmentation, Classification, and Registration of Multi-modality Medical Imaging Data, s. 80-86, 2021
- DOI för Learning a Deformable Registration Pyramid
- Ladda ner fulltext (pdf) av Learning a Deformable Registration Pyramid
-
Accurate 3D Object Detection using Energy-Based Models
Ingår i 2021 IEEE/CVF Conference on Computer Vision and Pattern Recogition Workshops (CVPRW 2021), s. 2849-2858, 2021
-
Learning deep autoregressive models for hierarchical data
Ingår i IFAC PapersOnLine, s. 529-534, 2021
- DOI för Learning deep autoregressive models for hierarchical data
- Ladda ner fulltext (pdf) av Learning deep autoregressive models for hierarchical data
-
Deep State Space Models for Nonlinear System Identification
Ingår i IFAC PapersOnLine, s. 481-486, 2021
- DOI för Deep State Space Models for Nonlinear System Identification
- Ladda ner fulltext (pdf) av Deep State Space Models for Nonlinear System Identification
-
First Steps Towards Self-Supervised Pretraining of the 12-Lead ECG
Ingår i 2021 Computing In Cardiology (CINC), 2021
-
How convolutional neural networks deal with aliasing
Ingår i 2021 IEEE International Conference On Acoustics, Speech And Signal Processing (ICASSP 2021), s. 2755-2759, 2021
-
Willems' fundamental lemma based on second-order moments
Ingår i 2021 60th IEEE Conference On Decision And Control (CDC), s. 396-401, 2021
-
Variational State and Parameter Estimation
Ingår i IFAC PapersOnLine, s. 732-737, 2021
- DOI för Variational State and Parameter Estimation
- Ladda ner fulltext (pdf) av Variational State and Parameter Estimation
-
Bayes Control of Hammerstein Systems
Ingår i IFAC PapersOnLine, s. 755-760, 2021
- DOI för Bayes Control of Hammerstein Systems
- Ladda ner fulltext (pdf) av Bayes Control of Hammerstein Systems
-
Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics
Ingår i IFAC PapersOnLine, s. 97-102, 2021
- DOI för Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics
- Ladda ner fulltext (pdf) av Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics
-
Ingår i IFAC PapersOnLine, s. 505-510, 2021
-
Ingår i Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, s. 2370-2380, 2020
-
Energy-Based Models for Deep Probabilistic Regression
Ingår i Computer Vision – ECCV 2020, s. 325-343, 2020
-
Automatic 12-lead ECG Classification Using a Convolutional Network Ensemble
Ingår i 2020 Computing in Cardiology, 2020
-
How to Train Your Energy-Based Model for Regression
2020
-
Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision
Ingår i 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2020), s. 1289-1298, 2020
-
Optimistic robust linear quadratic dual control
Ingår i Proceedings of Machine Learning Research, VOL 120, s. 550-560, 2020
-
Ingår i The 35th Uncertainty in Artificial Intelligence Conference (UAI), s. 679-689, 2020
-
Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness
Ingår i Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), s. 2370-2380, 2020
-
Deep Learning and System Identification
Ingår i IFAC Papersonline, s. 1175-1181, 2020
- DOI för Deep Learning and System Identification
- Ladda ner fulltext (pdf) av Deep Learning and System Identification
-
Particle Filter with Rejection Control and Unbiased Estimator of the Marginal Likelihood
Ingår i ICASSP 2020, s. 5860-5864, 2020
-
A fast quasi-Newton-type method for large-scale stochastic optimisation
Ingår i IFAC PapersOnline, s. 1249-1254, 2020
- DOI för A fast quasi-Newton-type method for large-scale stochastic optimisation
- Ladda ner fulltext (pdf) av A fast quasi-Newton-type method for large-scale stochastic optimisation
-
Bayesian identification of state-space models via adaptive thermostats
Ingår i 2019 IEEE 58th conference on decision and control (CDC), s. 7382-7388, 2019
-
Evaluating model calibration in classification
Ingår i 22nd International Conference on Artificial Intelligence and Statistics, s. 3459-3467, 2019
-
Inferring Heterogeneous Causal Effects in Presence of Spatial Confounding
Ingår i Proceedings of the 36th International Conference on Machine Learning, s. 4942-4950, 2019
-
Deep convolutional networks in system identification
Ingår i Proc. 58th IEEE Conference on Decision and Control, s. 3670-3676, 2019
-
Robust exploration in linear quadratic reinforcement learning
Ingår i Advances in Neural Information Processing Systems 32 (NIPS 2019), 2019
-
Conditionally Independent Multiresolution Gaussian Processes
Ingår i 22nd International Conference On Artificial Intelligence And Statistics, Vol 89, 2019
-
Automatic diagnosis of short-duration 12-lead ECG using a deep convolutional network
Ingår i ML4H: Machine Learning for Health Workshop at NeurIPS, Montréal, Canada, December 2018., 2018
-
Learning nonlinear state-space models using smooth particle-filter-based likelihood approximations
s. 652-657, 2018
-
Learning localized spatio-temporal models from streaming data
Ingår i Proceedings of the 35th International Conference on Machine Learning, s. 3927-3935, 2018
-
Regularized parametric system identification: a decision-theoretic formulation
Ingår i 2018 Annual American Control Conference (ACC), s. 1895-1900, 2018
-
Data-driven impulse response regularization via deep learning
s. 1-6, 2018
-
Delayed sampling and automatic Rao-Blackwellization of probabilistic programs
Ingår i Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS), Lanzarote, Spain, April, 2018, 2018
-
Auxiliary-Particle-Filter-based Two-Filter Smoothing for Wiener State-Space Models
Ingår i Proceedings of the 21st International Conference on Information Fusion, Cambridge, UK, July, 2018., s. 1904-1911, 2018
-
Learning convex bounds for linear quadratic control policy synthesis
Ingår i Neural Information Processing Systems 2018, 2018
-
How consistent is my model with the data?: Information-theoretic model check
s. 407-412, 2018
-
Probabilistic programming allows for automated inference in factor graph models
2018
-
Prediction Performance After Learning in Gaussian Process Regression
Ingår i Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, s. 1264-1272, 2017
-
Linearly constrained Gaussian processes
Ingår i Proc. 31st Conference on Neural Information Processing Systems, s. 1215-1224, 2017
-
On the construction of probabilistic Newton-type algorithms
Ingår i Proc. 56th Conference on Decision and Control, s. 6499-6504, 2017
-
Particle-based Gaussian process optimization for input design in nonlinear dynamical models
Ingår i 2016 IEEE 55th Conference On Decision And Control (CDC), s. 2085-2090, 2016
-
Computationally Efficient Bayesian Learning of Gaussian Process State Space Models
Ingår i Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, s. 213-221, 2016
-
Accelerometer calibration using sensor fusion with a gyroscope
Ingår i Proc. 19th Statistical Signal Processing Workshop, s. 660-664, 2016
- DOI för Accelerometer calibration using sensor fusion with a gyroscope
- Ladda ner fulltext (pdf) av Accelerometer calibration using sensor fusion with a gyroscope
-
Prediction performance after learning in Gaussian process regression
Ingår i 25th European Research Network System Identification Workshop, 2016
-
A scalable and distributed solution to the inertial motion capture problem
Ingår i Proc. 19th International Conference on Information Fusion, s. 1348-1355, 2016
-
Marginalizing Gaussian process hyperparameters using sequential Monte Carlo
Ingår i Proc. 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, s. 477-480, 2015
- DOI för Marginalizing Gaussian process hyperparameters using sequential Monte Carlo
- Ladda ner fulltext (pdf) av Marginalizing Gaussian process hyperparameters using sequential Monte Carlo
-
Particle filtering based identification for autonomous nonlinear ODE models
Ingår i Proc. 17th IFAC Symposium on System Identification, s. 415-420, 2015
-
Nonlinear state space model identification using a regularized basis function expansion
Ingår i Proc. 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, s. 481-484, 2015
-
Nonlinear state space smoothing using the conditional particle filter
Ingår i Proc. 17th IFAC Symposium on System Identification, s. 975-980, 2015
-
Bayesian nonparametric identification of piecewise affine ARX systems
s. 709-714, 2015
-
On Identification via EM with Latent Disturbances and Lagrangian Relaxation
s. 69-74, 2015
-
Identification of jump Markov linear models using particle filters
Ingår i Proc. 53rd Conference on Decision and Control, s. 6504-6509, 2014
-
Robust auxiliary particle filters using multiple importance sampling
Ingår i Proc. 18th Workshop on Statistical Signal Processing, s. 268-271, 2014
-
Backward sequential Monte Carlo for marginal smoothing
Ingår i Proc. 18th Workshop on Statistical Signal Processing, s. 368-371, 2014