{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T05:58:45Z","timestamp":1772171925710,"version":"3.50.1"},"reference-count":77,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Research Council of Finland","doi-asserted-by":"crossref","award":["336357"],"award-info":[{"award-number":["336357"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Inverse problems are often described as limited-data problems in which the signal of interest cannot be observed directly. Therefore, a physics-based forward model that relates the signal with the observations is typically needed. Unfortunately, unknown model parameters and imperfect forward models can still undermine the signal recovery. Even though supervised machine learning techniques offer promising avenues to improve the robustness of the solutions, we have to rely on model-based learning when there is no access to ground truth for the training. In this work, we studied a linear inverse problem that included an unknown non-linearly related model parameter and utilized a Bayesian model-based learning approach that allowed reliable signal recovery and subsequently estimation of the unknown model parameter. This approach, often referred to as Bayesian approximation error approach, employed a simplified model of the physics of the problem augmented with an approximation error term that compensated for the simplification. An error subspace was spanned with the help of the eigenvectors of the approximation error covariance matrix which allowed, alongside the primary signal, simultaneous estimation of the induced error. The estimated error and signal were then used to determine the unknown model parameter. For the model parameter estimation, we tested several different approaches: a conditional Gaussian regression, an iterative (model-based) optimization, and a Gaussian process that was modeled with the help of physics-informed learning. In addition, alternating optimization was used as a reference method. As an example application, we focused on the problem of reconstructing brain activity from EEG recordings (a.k.a. EEG source imaging) under the condition that the electrical conductivity of the patient\u2019s skull was unknown in the model. Poorly selected conductivity values cause well-documented artifacts in the EEG source imaging results, and the determination of patient-specific head tissue conductivities is a significant technical problem. Our results demonstrated clear improvements in EEG source localization accuracy and provided feasible estimates for the unknown model parameter, skull conductivity.<\/jats:p>","DOI":"10.1088\/2632-2153\/aded57","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T09:24:21Z","timestamp":1752139461000},"page":"035020","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Bayesian model parameter learning in linear inverse problems: application in EEG focal source imaging"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7605-3844","authenticated-orcid":true,"given":"Alexandra","family":"Koulouri","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8679-7898","authenticated-orcid":true,"given":"Ville","family":"Rimpil\u00e4inen","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,8,4]]},"reference":[{"key":"mlstaded57bib1","author":"Kirsch","year":"1996"},{"key":"mlstaded57bib2","first-page":"195","article-title":"On the stability of inverse problems","volume":"39","author":"Tikhonov","year":"1943","journal-title":"Dokl. Akad. Nauk SSSR"},{"key":"mlstaded57bib3","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/BF01386397","article-title":"On the regularization of projection methods for solving ill-posed problems","volume":"57","author":"Plato","year":"1990","journal-title":"Numer. Math."},{"key":"mlstaded57bib4","author":"Engl","year":"1996"},{"key":"mlstaded57bib5","author":"Hansen","year":"1998"},{"key":"mlstaded57bib6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/s0962492918000016","article-title":"Modern regularization methods for inverse problems","volume":"27","author":"Benning","year":"2018","journal-title":"Acta Numer."},{"key":"mlstaded57bib7","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ac245d","article-title":"Learning regularization parameters of inverse problems via deep neural networks","volume":"37","author":"Afkham","year":"2021","journal-title":"Inverse Problems"},{"key":"mlstaded57bib8","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1109\/tsp.2023.3263363","article-title":"Regularized linear regression via covariance fitting","volume":"71","author":"Mattsson","year":"2023","journal-title":"IEEE Trans. Signal Process."},{"key":"mlstaded57bib9","author":"Burger","year":"2013"},{"key":"mlstaded57bib10","doi-asserted-by":"crossref","DOI":"10.1201\/9781420007299.ch5","article-title":"Deconvolution of medical images from microscopic to whole body images","author":"Michailovich","year":"2007"},{"key":"mlstaded57bib11","article-title":"Auto-calibration and biconvex compressive sensing with applications to parallel MRI","author":"Ni","year":"2024"},{"key":"mlstaded57bib12","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1109\/tit.2013.2294644","article-title":"Blind deconvolution using convex programming","volume":"60","author":"Ahmed","year":"2014","journal-title":"IEEE Trans. Inf. Theory"},{"key":"mlstaded57bib13","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/31\/11\/115002","article-title":"Self-calibration and biconvex compressive sensing","volume":"31","author":"Ling","year":"2015","journal-title":"Inverse Problems"},{"key":"mlstaded57bib14","article-title":"Alternating proximal algorithm for blind image recovery 2010","author":"Bolte","year":"2010"},{"key":"mlstaded57bib15","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1016\/j.acha.2018.01.001","article-title":"Rapid, robust, and reliable blind deconvolution via nonconvex optimization","volume":"47","author":"Li","year":"2019","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"mlstaded57bib16","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aa9581","article-title":"Solving ill-posed inverse problems using iterative deep neural networks","volume":"33","author":"Adler","year":"2017","journal-title":"Inverse Problems"},{"key":"mlstaded57bib17","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1109\/tmi.2018.2799231","article-title":"Learned primal-dual reconstruction","volume":"37","author":"Adler","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstaded57bib18","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/tip.2017.2713099","article-title":"Deep convolutional neural network for inverse problems in imaging","volume":"26","author":"Jin","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"mlstaded57bib19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/s0962492919000059","article-title":"Solving inverse problems using data-driven models","volume":"28","author":"Arridge","year":"2019","journal-title":"Acta Numer."},{"key":"mlstaded57bib20","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1137\/20m1338460","article-title":"On learned operator correction in inverse problems","volume":"14","author":"Lunz","year":"2021","journal-title":"SIAM J. Imaging Sci."},{"key":"mlstaded57bib21","article-title":"Inverse problems with learned forward operators","author":"Arridge","year":"2023"},{"key":"mlstaded57bib22","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"mlstaded57bib23","author":"Murphy","year":"2022"},{"key":"mlstaded57bib24","author":"Kaipio","year":"2004"},{"key":"mlstaded57bib25","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1016\/j.cam.2005.09.027","article-title":"Statistical inverse problems: Discretization, model reduction and inverse crimes","volume":"198","author":"Kaipio","year":"2007","journal-title":"J. Comput. Appl. Math."},{"key":"mlstaded57bib26","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1007\/BF02345748","article-title":"Dipole location errors in electroencephalogram source analysis due to volume conductor model errors","volume":"38","author":"Vanrumste","year":"2000","journal-title":"Med. Biol. Eng. Comput."},{"key":"mlstaded57bib27","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1002\/hbm.21114","article-title":"Modeling of the human skull in EEG source analysis","volume":"32","author":"Dannhauer","year":"2011","journal-title":"Hum. Brain Mapp."},{"key":"mlstaded57bib28","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.neuroimage.2013.03.017","article-title":"Effects of sutures and fontanels on MEG and EEG source analysis in a realistic infant head model","volume":"76","author":"Lew","year":"2013","journal-title":"NeuroImage"},{"key":"mlstaded57bib29","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/S1350-4533(99)00038-7","article-title":"Effects of local skull inhomogeneities on EEG source estimation","volume":"21","author":"Ollikainen","year":"1999","journal-title":"Med. Eng. Phys."},{"key":"mlstaded57bib30","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s10548-013-0313-y","article-title":"Influence of skull modeling approaches on EEG source localization","volume":"27","author":"Montes-Restrepo","year":"2014","journal-title":"Brain Topogr."},{"key":"mlstaded57bib31","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1016\/j.neuroimage.2018.11.058","article-title":"Improved EEG source localization with bayesian uncertainty modelling of unknown skull conductivity","volume":"188","author":"Rimpilainen","year":"2019","journal-title":"NeuroImage"},{"key":"mlstaded57bib32","doi-asserted-by":"publisher","first-page":"531","DOI":"10.3389\/fnins.2019.00531","article-title":"Influence of head tissue conductivity uncertainties on EEG dipole reconstruction","volume":"13","author":"Vorwerk","year":"2019","journal-title":"Front. Neurosci."},{"key":"mlstaded57bib33","doi-asserted-by":"publisher","first-page":"2862","DOI":"10.1002\/hbm.20714","article-title":"Improved EEG source analysis using low-resolution conductivity estimation in a four-compartment finite element head model","volume":"30","author":"Lew","year":"2009","journal-title":"Hum. Brain Mapp."},{"key":"mlstaded57bib34","article-title":"Patient specific conductivity models: characterization of the skull bones","author":"Papageorgakis","year":"2017"},{"key":"mlstaded57bib35","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/S0013-4694(98)00046-7","article-title":"Improving source reconstructions by combining bioelectric and biomagnetic data","volume":"107","author":"Fuchs","year":"1998","journal-title":"Electroencephalogr. Clin. Neurophysiol."},{"key":"mlstaded57bib36","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1016\/j.neuroimage.2007.06.002","article-title":"A novel integrated MEG and EEG analysis method for dipolar sources","volume":"37","author":"Huang","year":"2007","journal-title":"NeuroImage"},{"key":"mlstaded57bib37","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118753","article-title":"Combining EEG and MEG for the reconstruction of epileptic activity using a calibrated realistic volume conductor model","volume":"9","author":"Aydin","year":"2014","journal-title":"PLoS One"},{"key":"mlstaded57bib38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.117353","article-title":"Inter-subject variability of skull conductivity and thickness in calibrated realistic head models","volume":"223","author":"Antonakakis","year":"2020","journal-title":"NeuroImage"},{"key":"mlstaded57bib39","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/12\/4\/046028","article-title":"Impact of uncertain head tissue conductivity in the optimization of transcranial direct current stimulation for an auditory target","volume":"12","author":"Schmidt","year":"2015","journal-title":"J. Neural Eng."},{"key":"mlstaded57bib40","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1016\/j.neuroimage.2018.12.053","article-title":"A principled approach to conductivity uncertainty analysis in electric field calculations","volume":"188","author":"Saturnino","year":"2019","journal-title":"NeuroImage"},{"key":"mlstaded57bib41","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ac0547","article-title":"Does participant\u2019s age impact on tdcs induced fields? Insights from computational simulations","volume":"7","author":"McCann","year":"2021","journal-title":"Biomed. Phys. Eng. Express"},{"key":"mlstaded57bib42","article-title":"Approximate marginalization over modeling errors and uncertainties in inverse problems","author":"Kaipio","year":"2013"},{"key":"mlstaded57bib43","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1615\/Int.J.UncertaintyQuantification.v1.i3.20","article-title":"Reconstruction of domain boundary and conductivity in electrical impedance tomography using the approximation error approach","volume":"1","author":"Nissinen","year":"2011","journal-title":"Int. J. Uncertainty Quantif."},{"key":"mlstaded57bib44","first-page":"pp 1019","article-title":"Simultaneous skull conductivity and focal source imaging from EEG recordings with the help of Bayesian uncertainty modelling","author":"Koulouri","year":"2020"},{"key":"mlstaded57bib45","doi-asserted-by":"publisher","DOI":"10.1088\/0957-0233\/22\/10\/104013","article-title":"Nonstationary approximation error approach to imaging of three-dimensional pipe flow: experimental evaluation","volume":"22","author":"Lipponen","year":"2011","journal-title":"Meas. Sci. Technol."},{"key":"mlstaded57bib46","doi-asserted-by":"publisher","DOI":"10.1088\/0957-0233\/20\/10\/105504","article-title":"Compensation of errors due to discretization, domain truncation and unknown contact impedances in electrical impedance tomography","volume":"20","author":"Nissinen","year":"2009","journal-title":"Meas. Sci. Technol."},{"key":"mlstaded57bib47","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1088\/0266-5611\/22\/1\/010","article-title":"Approximation errors and model reduction with an application in optical diffusion tomography","volume":"22","author":"Arridge","year":"2006","journal-title":"Inverse Problems"},{"key":"mlstaded57bib48","doi-asserted-by":"publisher","first-page":"2257","DOI":"10.1364\/JOSAA.26.002257","article-title":"Approximation errors and model reduction in three-dimensional diffuse optical tomography","volume":"26","author":"Kolehmainen","year":"2009","journal-title":"J. Opt. Soc. Am. A"},{"key":"mlstaded57bib49","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/26\/1\/015005","article-title":"An approximation error approach for compensating for modelling errors between the radiative transfer equation and the diffusion approximation in diffuse optical tomography","volume":"26","author":"Tarvainen","year":"2010","journal-title":"Inverse Problems"},{"key":"mlstaded57bib50","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.apnum.2016.01.005","article-title":"Compensation of domain modelling errors in the inverse source problem of the Poisson equation: Application in electroencephalographic imaging","volume":"106","author":"Koulouri","year":"2016","journal-title":"Appl. Num. Math."},{"key":"mlstaded57bib51","doi-asserted-by":"crossref","first-page":"2015","DOI":"10.1364\/BOE.4.002015","article-title":"Compensation of optode sensitivity and position errors in diffuse optical tomography using the approximation error approach","volume":"4","author":"Mozumder","year":"2013","journal-title":"Biomed. Opt. Express"},{"key":"mlstaded57bib52","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ad602e","article-title":"Optimal design of large-scale nonlinear bayesian inverse problems under model uncertainty","volume":"40","author":"Alexanderian","year":"2024","journal-title":"Inverse Problems"},{"key":"mlstaded57bib53","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ac346a","article-title":"Approximation error method for imaging the human head by electrical impedance tomography","volume":"37","author":"Candiani","year":"2021","journal-title":"Inverse Problems"},{"key":"mlstaded57bib54","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/acc129","article-title":"On global normal linear approximations for nonlinear bayesian inverse problems","volume":"39","author":"Nicholson","year":"2023","journal-title":"Inverse Problems"},{"key":"mlstaded57bib55","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.1080\/01621459.1969.10501069","article-title":"On the exact covariance of products of random variables","volume":"64","author":"Bohrnstedt","year":"1969","journal-title":"J. Am. Stat. Assoc."},{"key":"mlstaded57bib56","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1186\/1743-0003-5-25","article-title":"Review on solving the inverse problem in EEG source analysis","volume":"5","author":"Grech","year":"2008","journal-title":"J. Neuroeng. Rehabil."},{"key":"mlstaded57bib57","doi-asserted-by":"publisher","first-page":"325","DOI":"10.3389\/fneur.2019.00325","article-title":"EEG source imaging: A practical review of the analysis steps","volume":"10","author":"Michel","year":"2019","journal-title":"Front. Neurol."},{"key":"mlstaded57bib58","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1109\/TBME.2002.807661","article-title":"Statistical performance analysis of signal variance-based dipole models for MEG\/EEG source localization and detection","volume":"50","author":"Rodriguez-Rivera","year":"2003","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"mlstaded57bib59","author":"H\u00f6ltershinken","year":"2024"},{"key":"mlstaded57bib60","article-title":"Solutions of the neuroelectromagnetic inverse problem: an evaluation study","author":"Kn\u00f6sche","year":"1997"},{"key":"mlstaded57bib61","article-title":"Electrical impedance tomography and prior information","author":"Vauhkonen","year":"1997"},{"key":"mlstaded57bib62","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.117044","article-title":"Accurate and robust whole-head segmentation from magnetic resonance images for individualized head modeling","volume":"219","author":"Puonti","year":"2020","journal-title":"NeuroImage"},{"key":"mlstaded57bib63","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1088\/0266-5611\/20\/4\/007","article-title":"Efficient computation of lead field bases and influence matrix for the FEM-based EEG and MEG inverse problem","volume":"20","author":"Wolters","year":"2004","journal-title":"Inverse Problems"},{"key":"mlstaded57bib64","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1023\/A:1025606415858","article-title":"Measurement of the conductivity of skull, temporarily removed during epilepsy surgery","volume":"16","author":"Hoekema","year":"2003","journal-title":"Brain Topogr."},{"key":"mlstaded57bib65","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/0168-0102(95)00880-3","article-title":"Conductivity ratios of the scalp-skull-brain head model in estimating equivalent dipole sources in human brain","volume":"22","author":"Homma","year":"1995","journal-title":"Neurosci. Res."},{"key":"mlstaded57bib66","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/1475-925X-5-10","article-title":"Influence of head models on EEG simulations and inverse source localizations","volume":"5","author":"Ramon","year":"2006","journal-title":"Biomed. Eng. Online"},{"key":"mlstaded57bib67","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1088\/0266-5611\/14\/4\/008","article-title":"Some remarks on the problem of source identification from boundary measurements","volume":"14","author":"Badia","year":"1998","journal-title":"Inverse Problems"},{"key":"mlstaded57bib68","first-page":"pp 812","article-title":"Depth normalization in MEG\/EEG current density imaging","volume":"vol 2)","author":"K\u00f6hler","year":"1996"},{"key":"mlstaded57bib69","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/0167-8760(84)90014-X","article-title":"Low resolution electromagnetic tomography: a new method for localizing electrical activity in the brain","volume":"18","author":"Pascual-Marqui","year":"1994","journal-title":"Int. J. Psychophysiol."},{"key":"mlstaded57bib70","first-page":"5","article-title":"Standardized low resolution brain electromagnetic tomography (sLORETA): technical details","volume":"24","author":"Pascual-Marqui","year":"2002","journal-title":"Methods Find Exp. Clin. Pharmacol."},{"key":"mlstaded57bib71","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1097\/00004691-199905000-00006","article-title":"Linear and Nonlinear Current Density Reconstructions","volume":"16","author":"Fuchs","year":"1999","journal-title":"J. Clin. Neurophysiol."},{"key":"mlstaded57bib72","first-page":"pp 393","author":"Wagner","year":"2000"},{"key":"mlstaded57bib73","doi-asserted-by":"publisher","first-page":"1783","DOI":"10.1088\/0031-9155\/52\/7\/002","article-title":"swLORETA: a novel approach to robust source localization and synchronization tomography","volume":"52","author":"Palmero-Soler","year":"2007","journal-title":"Phys. Med. Biol."},{"key":"mlstaded57bib74","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/S0013-4694(96)95698-9","article-title":"Inverse localization of electric dipole current sources in finite element models of the human head","volume":"102","author":"Buchner","year":"1997","journal-title":"Electroencephalogr. Clin. Neurophysiol."},{"key":"mlstaded57bib75","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1016\/j.neuroimage.2013.10.027","article-title":"MNE software for processing MEG and EEG data","volume":"86","author":"Gramfort","year":"2014","journal-title":"NeuroImage"},{"key":"mlstaded57bib76","first-page":"pp 33","author":"Koulouri","year":"2018"},{"key":"mlstaded57bib77","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/s10548-018-0670-7","article-title":"Brain activity mapping from meg data via a hierarchical bayesian algorithm with automatic depth weighting","volume":"32","author":"Calvetti","year":"2018","journal-title":"Brain Topogr."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded57","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded57\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded57","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded57\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded57\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded57\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded57\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded57\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T08:25:11Z","timestamp":1754295911000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":77,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,8,4]]},"published-print":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/aded57","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,4]]},"assertion":[{"value":"Bayesian model parameter learning in linear inverse problems: application in EEG focal source imaging","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-01-03","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-07-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-08-04","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}