{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T13:09:36Z","timestamp":1747141776348},"reference-count":69,"publisher":"MIT Press","issue":"8","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,26]]},"abstract":"<jats:p>Many natural systems, especially biological ones, exhibit complex multivariate nonlinear dynamical behaviors that can be hard to capture by linear autoregressive models. On the other hand, generic nonlinear models such as deep recurrent neural networks often require large amounts of training data, not always available in domains such as brain imaging; also, they often lack interpretability. Domain knowledge about the types of dynamics typically observed in such systems, such as a certain type of dynamical systems models, could complement purely data-driven techniques by providing a good prior. In this work, we consider a class of ordinary differential equation (ODE) models known as van der Pol (VDP) oscil lators and evaluate their ability to capture a low-dimensional representation of neural activity measured by different brain imaging modalities, such as calcium imaging (CaI) and fMRI, in different living organisms: larval zebrafish, rat, and human. We develop a novel and efficient approach to the nontrivial problem of parameters estimation for a network of coupled dynamical systems from multivariate data and demonstrate that the resulting VDP models are both accurate and interpretable, as VDP's coupling matrix reveals anatomically meaningful excitatory and inhibitory interactions across different brain subsystems. VDP outperforms linear autoregressive models (VAR) in terms of both the data fit accuracy and the quality of insight provided by the coupling matrices and often tends to generalize better to unseen data when predicting future brain activity, being comparable to and sometimes better than the recurrent neural networks (LSTMs). Finally, we demonstrate that our (generative) VDP model can also serve as a data-augmentation tool leading to marked improvements in predictive accuracy of recurrent neural networks. Thus, our work contributes to both basic and applied dimensions of neuroimaging: gaining scientific insights and improving brain-based predictive models, an area of potentially high practical importance in clinical diagnosis and neurotechnology.<\/jats:p>","DOI":"10.1162\/neco_a_01401","type":"journal-article","created":{"date-parts":[[2021,6,7]],"date-time":"2021-06-07T21:38:52Z","timestamp":1623101932000},"page":"2087-2127","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":4,"title":["Learning Brain Dynamics With Coupled Low-Dimensional Nonlinear Oscillators and Deep Recurrent Networks"],"prefix":"10.1162","volume":"33","author":[{"given":"Germ\u00e1n","family":"Abrevaya","sequence":"first","affiliation":[{"name":"Departamento de F\u00edsica, FCEyN, UBA and IFIBA, CONICET, 1428 Buenos Aires, Argentina gabrevaya@df.uba.ar"}]},{"given":"Guillaume","family":"Dumas","sequence":"additional","affiliation":[{"name":"Mila\u2013Quebec Artificial Intelligence Institute, and CHU Sainte-Justine Research Center, Department of Psychiatry, Universit\u00e9de Montr\u00e9al, Montreal H3A OE8, Canada guillaume.dumas@ppsp.team"}]},{"given":"Aleksandr Y.","family":"Aravkin","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA 98195, U.S.A. saravkin@uw.edu"}]},{"given":"Peng","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA 98195, U.S.A. zhengp@uw.edu"}]},{"given":"Jean-Christophe","family":"Gagnon-Audet","sequence":"additional","affiliation":[{"name":"Mila\u2013Quebec Artificial Intelligence Institute, Universit\u00e9de Montr\u00e9al, Montreal H3A OE8, Canada jean-christophe.gagnon-audet@mila.quebec"}]},{"given":"James","family":"Kozloski","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, U.S.A. kozloski@us.ibm.com"}]},{"given":"Pablo","family":"Polosecki","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, U.S.A. pipolose@us.ibm.com"}]},{"given":"Guillaume","family":"Lajoie","sequence":"additional","affiliation":[{"name":"Mila\u2013Quebec Artificial Intelligence Institute, Universit\u00e9de Montr\u00e9al, Montreal H3A OE8, Canada g.lajoie@umontreal.ca"}]},{"given":"David","family":"Cox","sequence":"additional","affiliation":[{"name":"MIT-IBM Watson AI Lab, Cambridge, MA 02139, U.S.A. David.D.Cox@ibm.com"}]},{"given":"Silvina Ponce","family":"Dawson","sequence":"additional","affiliation":[{"name":"Departamento de F\u00edsica, FCEyN, UBA and IFIBA, CONICET, 1428 Buenos Aires, Argentina silvina@df.uba.ar"}]},{"given":"Guillermo","family":"Cecchi","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, U.S.A. gcecchi@us.ibm.com"}]},{"given":"Irina","family":"Rish","sequence":"additional","affiliation":[{"name":"Mila\u2013Quebec Artificial Intelligence Institute, Universit\u00e9 de Montr\u00e9al, Montreal H3A OE8, Canada irina.rish@mila.quebec"}]}],"member":"281","published-online":{"date-parts":[[2021,7,26]]},"reference":[{"issue":"7399","key":"2021072618251476400_B1","doi-asserted-by":"crossref","DOI":"10.1038\/nature11057","article-title":"Brain-wide neuronal dynamics during motor adaptation in zebrafish","volume":"485","author":"Ahrens","year":"2012","journal-title":"Nature"},{"key":"2021072618251476400_B2","article-title":"Whole-brain imaging of neuronal activity in a larval zebrafish.","author":"Ahrens","year":"2013"},{"issue":"5","key":"2021072618251476400_B3","doi-asserted-by":"crossref","DOI":"10.1038\/nmeth.2434","article-title":"Whole-brain functional imaging at cellular resolution using light-sheet microscopy","volume":"10","author":"Ahrens","year":"2013","journal-title":"Nature Methods"},{"issue":"1","key":"2021072618251476400_B4","article-title":"Single-trial classification of awareness state during anesthesia by measuring critical dynamics of global brain activity","volume":"9","author":"Alonso","year":"2019","journal-title":"Scientific Reports"},{"key":"2021072618251476400_B5","author":"Anderson","year":"1979","journal-title":"Optimal filtering."},{"key":"2021072618251476400_B6","first-page":"3270","volume-title":"Advances in neural information processing systems","author":"Apthorpe","year":"2016"},{"issue":"12","key":"2021072618251476400_B7","doi-asserted-by":"crossref","first-page":"2898","DOI":"10.1109\/TAC.2011.2141430","article-title":"An l1-Laplace robust Kalman smoother","volume":"56","author":"Aravkin","year":"2011","journal-title":"IEEE Transactions on Automatic Control"},{"key":"2021072618251476400_B8","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.automatica.2017.08.011","article-title":"Generalized Kalman smoothing: Modeling and algorithms","volume":"86","author":"Aravkin","year":"2017","journal-title":"Automatica"},{"issue":"5","key":"2021072618251476400_B9","doi-asserted-by":"crossref","first-page":"2891","DOI":"10.1137\/130918861","article-title":"Robust and trend-following Student's-t Kalman smoothers","volume":"52","author":"Aravkin","year":"2014","journal-title":"SIAM Journal on Control and Optimization"},{"issue":"7","key":"2021072618251476400_B10","doi-asserted-by":"crossref","first-page":"2131","DOI":"10.1109\/TAC.2017.2754474","article-title":"Efficient quadratic penalization through the partial minimization technique","volume":"63","author":"Aravkin","year":"2018","journal-title":"IEEE Transactions on Automatic Control"},{"key":"2021072618251476400_B11","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.neuroimage.2014.07.045","article-title":"Impact of autocorrelation on functional connectivity","volume":"102","author":"Arbabshirani","year":"2014","journal-title":"NeuroImage"},{"issue":"3","key":"2021072618251476400_B12","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1109\/78.824682","article-title":"The marginal likelihood for parameters in a discrete Gauss Markov process.","volume":"48","author":"Bell","year":"2000","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"1","key":"2021072618251476400_B13","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.automatica.2008.05.029","article-title":"An inequality constrained nonlinear Kalman-Bucy smoother by interior point likelihood maximization","volume":"45","author":"Bell","year":"2009","journal-title":"Automatica"},{"issue":"1","key":"2021072618251476400_B14","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1162\/netn_a_00121","article-title":"Organizing principles of whole-brain functional connectivity in zebrafish larvae","volume":"4","author":"Betzel","year":"2020","journal-title":"Network Neuroscience"},{"issue":"1","key":"2021072618251476400_B15","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1137\/141000671","article-title":"Julia: A fresh approach to numerical computing.","volume":"59","author":"Bezanson","year":"2017","journal-title":"SIAM Review"},{"issue":"20","key":"2021072618251476400_B16","doi-asserted-by":"crossref","first-page":"6252","DOI":"10.1073\/pnas.1507708112","article-title":"Nonlinearity and chaos in ecological dynamics revisited","volume":"112","author":"Bj\u00f8rnstad","year":"2015","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2021072618251476400_B17","doi-asserted-by":"crossref","DOI":"10.1016\/j.conb.2019.06.008","article-title":"Data-driven models in human neuroscience and neuroengineering.","volume":"58","author":"Brunton","year":"2019","journal-title":"Current Opinion in Neurobiology"},{"issue":"4","key":"2021072618251476400_B18","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.tins.2019.02.001","article-title":"Exploration, inference, and prediction in neuroscience and biomedicine","volume":"42","author":"Bzdok","year":"2019","journal-title":"Trends in Neurosciences"},{"issue":"10","key":"2021072618251476400_B19","doi-asserted-by":"crossref","first-page":"3610","DOI":"10.1093\/cercor\/bhx233","article-title":"Random recurrent networks near criticality capture the broadband power distribution of human ECoG dynamics","volume":"28","author":"Chaudhuri","year":"2018","journal-title":"Cerebral Cortex"},{"issue":"2","key":"2021072618251476400_B20","first-page":"379","article-title":"Kalman filter with outliers and missing observations","volume":"6","author":"Cipra","year":"1997","journal-title":"Sociedad de Estadistica e Invastigacion Operativa"},{"issue":"1","key":"2021072618251476400_B21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00422-009-0328-3","article-title":"The Wilson\u2013Cowan model, 36 years later","volume":"101","author":"Destexhe","year":"2009","journal-title":"Biological Cybernetics"},{"issue":"6","key":"2021072618251476400_B22","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1109\/9.769393","article-title":"Robust estimation with unknown noise statistics","volume":"44","author":"Durovic","year":"1999","journal-title":"IEEE Transactions on Automatic Control"},{"key":"2021072618251476400_B23","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-87708-2","author":"Ermentrout","year":"2010","journal-title":"Mathematical foundations of neuroscience"},{"issue":"12","key":"2021072618251476400_B24","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0015710","article-title":"Multiplexed echo planar imaging for sub-second whole brain FMRI and fast diffusion imaging","volume":"5","author":"Feinberg","year":"2010","journal-title":"PLOS One"},{"issue":"6","key":"2021072618251476400_B25","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/S0006-3495(61)86902-6","article-title":"Impulses and physiological states in theoretical models of nerve membrane","volume":"1","author":"FitzHugh","year":"1961","journal-title":"Biophysical Journal"},{"key":"2021072618251476400_B26","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1016\/j.neuroimage.2018.05.058","article-title":"A generative model of whole-brain effective connectivity","volume":"179","author":"Fr\u00e4ssle","year":"2018","journal-title":"NeuroImage"},{"issue":"1","key":"2021072618251476400_B27","doi-asserted-by":"crossref","DOI":"10.1186\/s12918-015-0219-2","article-title":"Robust and efficient parameter estimation in dynamic models of biological systems","volume":"9","author":"G\u00e1bor","year":"2015","journal-title":"BMC Systems Biology"},{"key":"2021072618251476400_B28","first-page":"2381","volume-title":"Advances in neural information processing systems","author":"Giovannucci","year":"2017"},{"issue":"2","key":"2021072618251476400_B29","doi-asserted-by":"crossref","DOI":"10.1088\/0266-5611\/19\/2\/201","article-title":"Separable nonlinear least squares: The variable projection method and its applications","volume":"19","author":"Golub","year":"2003","journal-title":"Inverse Problems"},{"issue":"4","key":"2021072618251476400_B30","doi-asserted-by":"crossref","first-page":"2109","DOI":"10.1016\/j.neuroimage.2011.03.005","article-title":"Dynamic modeling of neuronal responses in FMRI using cubature Kalman filtering","volume":"56","author":"Havlicek","year":"2011","journal-title":"NeuroImage"},{"issue":"3","key":"2021072618251476400_B31","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1016\/j.acha.2020.06.005","article-title":"Data-driven spatiotemporal modal decomposition for time frequency analysis","volume":"49","author":"Hirsh","year":"2020","journal-title":"Applied and Computational Harmonic Analysis"},{"issue":"8","key":"2021072618251476400_B32","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory.","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"2021072618251476400_B33","author":"Hoppensteadt","year":"2012","journal-title":"Weakly connected neural networks"},{"key":"2021072618251476400_B34","first-page":"2901","volume-title":"Advances in neural information processing systems","author":"Inan","year":"2017"},{"key":"2021072618251476400_B35","author":"Izhikevich","year":"2007","journal-title":"Dynamical systems in neuroscience: The geometry of excitability and bursting"},{"issue":"1","key":"2021072618251476400_B36","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1115\/1.3662552","article-title":"A new approach to linear filtering and prediction problems","volume":"82","author":"Kalman","year":"1960","journal-title":"Journal of Basic Engineering"},{"issue":"1","key":"2021072618251476400_B37","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1115\/1.3658902","article-title":"New results in linear filtering and prediction theory","volume":"83","author":"Kalman","year":"1961","journal-title":"Journal of Basic Engineering"},{"issue":"1","key":"2021072618251476400_B38","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/BF00336943","article-title":"Coupled Van der Pol oscillators\u2014a model of excitatory and inhibitory neural interactions","volume":"39","author":"Kawahara","year":"1980","journal-title":"Biological Cybernetics"},{"issue":"2","key":"2021072618251476400_B39","article-title":"Compensation in preclinical Huntington's disease: Evidence from the track-on HD study.","volume":"10","author":"Kloeppel","year":"2015","journal-title":"EBioMedicine"},{"issue":"9","key":"2021072618251476400_B40","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.crvi.2003.09.011","article-title":"Is there chaos in the brain? II. Experimental evidence and related models","volume":"326","author":"Korn","year":"2003","journal-title":"Comptes rendus biologies"},{"key":"2021072618251476400_B41","doi-asserted-by":"crossref","DOI":"10.3389\/fncom.2019.00075","article-title":"Extracting reproducible time-resolved resting state networks using dynamic mode decomposition","volume":"13","author":"Kunert-Graf","year":"2019","journal-title":"Frontiers in Computational Neuroscience"},{"issue":"1","key":"2021072618251476400_B42","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1146\/annurev.neuro.24.1.263","article-title":"Odor encoding as an active, dynamical process: Experiments, computation, and theory","volume":"24","author":"Laurent","year":"2001","journal-title":"Annual Review of Neuroscience"},{"issue":"3","key":"2021072618251476400_B43","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1000696","article-title":"Parameter estimation and model selection in computational biology.","volume":"6","author":"Lillacci","year":"2010","journal-title":"PLOS Computational Biology"},{"key":"2021072618251476400_B44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-27752-1","author":"tkepohl","year":"2005","journal-title":"New introduction to multiple time series analysis"},{"issue":"406","key":"2021072618251476400_B45","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1080\/01621459.1989.10478794","article-title":"Robustification of Kalman filter models.","volume":"84","author":"Meinhold","year":"1989","journal-title":"Journal of the American Statistical Association"},{"issue":"6","key":"2021072618251476400_B46","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1093\/bib\/bbx044","article-title":"Deep learning for healthcare: Review, opportunities and challenges","volume":"19","author":"Miotto","year":"2018","journal-title":"Briefings in Bioinformatics"},{"key":"2021072618251476400_B47","author":"Moirogiannis","year":"2019","journal-title":"A center manifold reduction technique for a system of randomly coupled oscillators"},{"issue":"3\u20134","key":"2021072618251476400_B48","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1007\/s10955-017-1753-7","article-title":"Renormalization of collective modes in large-scale neural dynamics","volume":"167","author":"Moirogiannis","year":"2017","journal-title":"Journal of Statistical Physics"},{"issue":"6","key":"2021072618251476400_B49","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1007\/BF00925744","article-title":"Maximum-likelihood recursive nonlinear filtering","volume":"2","author":"Mortensen","year":"1968","journal-title":"Journal of Optimization Theory and Applications"},{"issue":"4","key":"2021072618251476400_B50","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1016\/j.cell.2016.10.019","article-title":"From whole-brain data to functional circuit models: The zebrafish optomotor response","volume":"167","author":"Naumann","year":"2016","journal-title":"Cell"},{"issue":"5","key":"2021072618251476400_B51","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1004209","article-title":"Computational modeling of seizure dynamics using coupled neuronal networks: Factors shaping epileptiform activity","volume":"11","author":"Naze","year":"2015","journal-title":"PLOS Comput. Biol."},{"key":"2021072618251476400_B52","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1016\/j.neuroimage.2017.11.033","article-title":"Dynamic effective connectivity in resting state FMRI","volume":"180","author":"Park","year":"2018","journal-title":"NeuroImage"},{"issue":"7","key":"2021072618251476400_B53","doi-asserted-by":"crossref","first-page":"3619","DOI":"10.1073\/pnas.97.7.3619","article-title":"Optical probing of neuronal circuits with calcium indicators","volume":"97","author":"Peterlin","year":"2000","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"23","key":"2021072618251476400_B54","doi-asserted-by":"crossref","first-page":"3209","DOI":"10.1093\/bioinformatics\/btm510","article-title":"Estimating parameters and hidden variables in non-linear state-space models based on ODEs for biological networks inference","volume":"23","author":"Quach","year":"2007","journal-title":"Bioinformatics"},{"key":"2021072618251476400_B55","author":"Rackauckas","year":"2020","journal-title":"Universal differential equations for scientific machine learning"},{"issue":"1","key":"2021072618251476400_B56","doi-asserted-by":"crossref","DOI":"10.5334\/jors.151","article-title":"Differential equations.jl: A performant and feature-rich ecosystem for solving differential equations in Julia.","volume":"5","author":"Rackauckas","year":"2017","journal-title":"Journal of Open Research Software"},{"issue":"34","key":"2021072618251476400_B57","doi-asserted-by":"crossref","first-page":"20890","DOI":"10.1073\/pnas.2003383117","article-title":"Hierarchical dynamics as a macroscopic organizing principle of the human brain","volume":"117","author":"Raut","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1","key":"2021072618251476400_B58","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2105-7-483","article-title":"Novel metaheuristic for parameter estimation in nonlinear dynamic biological systems","volume":"7","author":"Rodriguez-Fernandez","year":"2006","journal-title":"BMC Bioinformatics"},{"issue":"6","key":"2021072618251476400_B59","doi-asserted-by":"crossref","first-page":"4082","DOI":"10.1063\/1.533336","article-title":"Past and future of inverse problems","volume":"41","author":"Sabatier","year":"2000","journal-title":"Journal of Mathematical Physics"},{"issue":"6","key":"2021072618251476400_B60","doi-asserted-by":"crossref","DOI":"10.1038\/nmeth.2936","article-title":"Chronic, wireless recordings of large-scale brain activity in freely moving rhesus monkeys","volume":"11","author":"Schwarz","year":"2014","journal-title":"Nature Methods"},{"issue":"1","key":"2021072618251476400_B61","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/S0896-6273(00)81155-1","article-title":"Stability of the memory of eye position in a recurrent network of conductance-based model neurons","volume":"26","author":"Seung","year":"2000","journal-title":"Neuron"},{"key":"2021072618251476400_B62","author":"Shoeibi","year":"2020","journal-title":"Epileptic seizure detection using deep learning techniques: A review."},{"issue":"1","key":"2021072618251476400_B63","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevE.66.016210","article-title":"Estimation of parameters and unobserved components for nonlinear systems from noisy time series","volume":"66","author":"Sitz","year":"2002","journal-title":"Physical Review E"},{"key":"2021072618251476400_B64","first-page":"4024","volume-title":"Advances in neural information processing systems","author":"Speiser","year":"2017"},{"issue":"1","key":"2021072618251476400_B65","article-title":"A penalty method for PDE-constrained optimization in inverse problems","volume":"32","author":"van Leeuwen","year":"2015","journal-title":"Inverse Problems"},{"issue":"12","key":"2021072618251476400_B66","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1038\/s41592-018-0221-x","article-title":"Brain-wide circuit interrogation at the cellular level guided by online analysis of neuronal function","volume":"15","author":"Vladimirov","year":"2018","journal-title":"Nature Methods"},{"issue":"6","key":"2021072618251476400_B67","doi-asserted-by":"crossref","first-page":"1905","DOI":"10.1142\/S0218127404010345","article-title":"Nonlinear dynamical system identification from uncertain and indirect measurements","volume":"14","author":"Voss","year":"2004","journal-title":"International Journal of Bifurcation and Chaos"},{"key":"2021072618251476400_B68","author":"Wiggins","year":"2003","journal-title":"Introduction to applied nonlinear dynamical systems and chaos"},{"key":"2021072618251476400_B69","article-title":"A survey on deep learning-based non-invasive brain signals: Recent advances and new frontiers","volume":"18","author":"Zhang","year":"2020","journal-title":"Journal of Neural Engineering"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/direct.mit.edu\/neco\/article-pdf\/33\/8\/2087\/1930932\/neco_a_01401.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/direct.mit.edu\/neco\/article-pdf\/33\/8\/2087\/1930932\/neco_a_01401.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T06:57:02Z","timestamp":1672383422000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/33\/8\/2087\/101867\/Learning-Brain-Dynamics-With-Coupled-Low"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,26]]},"references-count":69,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,7,26]]},"published-print":{"date-parts":[[2021,7,26]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01401","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,8]]},"published":{"date-parts":[[2021,7,26]]}}}