{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T01:42:21Z","timestamp":1792201341294,"version":"4.4.0"},"reference-count":35,"publisher":"MIT Press","issue":"11","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,10,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This article presents a cortically motivated framework for geometry-aware sparse reservoir computing with efficient online readout adaptation. The architecture is based on FitzHugh-Nagumo units coupled through sparse connectivity motifs informed by cortical statistics (reciprocity, triadic closure, and Dale\u2019s law), resulting in a structured and biologically plausible recurrent matrix. The readout weights are trained by means of an anchor-proximal ridge objective applied to streaming time windows, ensuring temporally stable online learning with a low memory footprint. It presents the results of numerical experiments on a temporal decision-making benchmark and an image-based long-range segmentation task. The proposed sparse reservoir, combined with the windowed proximal readout, is shown to achieve competitive accuracy while substantially reducing recurrent and state-storage requirements. A favorable trade-off of biological plausibility, predictive performance, and computational efficiency is thereby demonstrated.<\/jats:p>","DOI":"10.1162\/neco.a.1578","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T17:41:01Z","timestamp":1790098861000},"page":"1982-2007","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":0,"title":["A Geometry-Aware Bio-Inspired Sparse Reservoir With Online Learning"],"prefix":"10.1162","volume":"38","author":[{"given":"Alfio","family":"Borz\u00ec","sequence":"first","affiliation":[{"name":"Institut f\u00fcr Mathematik, Universit\u00e4t W\u00fcrzburg, 97074 W\u00fcrzburg, Germany alfio.borzi@uni-wuerzburg.de"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2026,10,16]]},"reference":[{"key":"2026101621153175900_bib1","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1038\/s42005-024-01530-y","article-title":"Criticality in FitzHugh-Nagumo oscillator ensembles: Design, robustness, and spatial invariance","volume":"7","author":"Al Beattie","year":"2024","journal-title":"Communications Physics"},{"key":"2026101621153175900_bib2","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1038\/ncomms1476","article-title":"Information processing using a single dynamical node as complex system","volume":"2","author":"Appeltant","year":"2011","journal-title":"Nature Communications"},{"key":"2026101621153175900_bib3","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-48311-5","author":"Bauschke,","year":"2017","journal-title":"Convex analysis and monotone operator theory in Hilbert spaces"},{"issue":"3","key":"2026101621153175900_bib4","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1177\/003591573502800330","article-title":"Pharmacology and nerve-endings","volume":"28","author":"Dale","year":"1935","journal-title":"Journal of the Royal Society of Medicine"},{"issue":"6","key":"2026101621153175900_bib5","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1016\/S0959-4388(00)00153-7","article-title":"Complementary roles of basal ganglia and cerebellum in learning and motor control","volume":"10","author":"Doya","year":"2000","journal-title":"Current Opinion in Neurobiology"},{"issue":"2","key":"2026101621153175900_bib6","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1098\/rsnr.1976.0015","article-title":"From electrical to chemical transmission in the central nervous system: The closing address of the Sir Henry Dale Centennial Symposium Cambridge, 19 September 1975","volume":"30","author":"Eccles","year":"1976","journal-title":"Notes and Records of the Royal Society of London"},{"issue":"1","key":"2026101621153175900_bib7","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.neuron.2013.07.036","article-title":"A predictive network model of cerebral cortical connectivity based on a distance rule","volume":"80","author":"Ercsey-Ravasz","year":"2013","journal-title":"Neuron"},{"issue":"6","key":"2026101621153175900_bib8","doi-asserted-by":"publisher","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":"2026101621153175900_bib9","doi-asserted-by":"crossref","first-page":"85","DOI":"10.3389\/fncir.2015.00085","article-title":"Neuromodulated spike-timing-dependent plasticity, and theory of three-factor learning rules","volume":"9","author":"Fr\u00e9maux","year":"2016","journal-title":"Frontiers in Neural Circuits"},{"issue":"3","key":"2026101621153175900_bib10","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/s12559-017-9461-9","article-title":"Echo state property of deep reservoir computing networks","volume":"9","author":"Gallicchio","year":"2017","journal-title":"Cognitive Computation"},{"key":"2026101621153175900_bib11","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.neunet.2021.01.025","article-title":"Fading memory echo state networks are universal","volume":"138","author":"Gonon","year":"2021","journal-title":"Neural Networks"},{"key":"2026101621153175900_bib12","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1038\/nn.3917","article-title":"The neocortical circuit: Themes and variations","volume":"18","author":"Harris","year":"2015","journal-title":"Nature Neuroscience"},{"key":"2026101621153175900_bib13","author":"Haykin,","year":"2002","journal-title":"Adaptive filter theory"},{"key":"2026101621153175900_bib14","doi-asserted-by":"publisher","first-page":"113943","DOI":"10.1016\/j.cam.2021.113943","article-title":"A sequential quadratic Hamiltonian algorithm for training explicit RK neural networks","volume":"405","author":"Hofmann","year":"2022","journal-title":"Journal of Computational and Applied Mathematics"},{"key":"2026101621153175900_bib15","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.1137\/24M1675369","article-title":"The Pontryagin maximum principle for training convolutional neural networks","volume":"7","author":"Hofmann","year":"2025","journal-title":"SIAM Journal on Mathematics of Data Science"},{"key":"2026101621153175900_bib16","author":"Izhikevich,","year":"2007","journal-title":"Dynamical systems in neuroscience: The geometry of excitability and bursting"},{"key":"2026101621153175900_bib17","author":"Jaeger,","year":"2001","journal-title":"The \u201cecho state\u201d approach to analysing and training recurrent neural networks."},{"key":"2026101621153175900_bib18","author":"Jaeger,","year":"2002","journal-title":"Short term memory in echo state networks"},{"key":"2026101621153175900_bib19","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s12591-021-00569-5","article-title":"A nearly exact discretization scheme for the FitzHugh\u2013Nagumo model","volume":"32","author":"Kwessi","year":"2021","journal-title":"Differential Equations and Dynamical Systems"},{"key":"2026101621153175900_bib20","doi-asserted-by":"publisher","first-page":"041102","DOI":"10.1063\/1.4979665","article-title":"Reservoir observers: Model-free inference of unmeasured variables in chaotic systems","volume":"27","author":"Lu","year":"2017","journal-title":"Chaos"},{"issue":"3","key":"2026101621153175900_bib21","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.cosrev.2009.03.005","article-title":"Reservoir computing approaches to recurrent neural network training","volume":"3","author":"Luko\u0161evi\u010dius","year":"2009","journal-title":"Computer Science Review"},{"issue":"11","key":"2026101621153175900_bib22","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1162\/089976602760407955","article-title":"Real-time computing without stable states: A new framework for neural computation based on perturbations","volume":"14","author":"Maass","year":"2002","journal-title":"Neural Computation"},{"issue":"10","key":"2026101621153175900_bib23","doi-asserted-by":"publisher","first-page":"2061","DOI":"10.1109\/JRPROC.1962.288235","article-title":"An active pulse transmission line simulating nerve axon","volume":"50","author":"Nagumo","year":"1962","journal-title":"Proceedings of the IRE"},{"issue":"6","key":"2026101621153175900_bib24","doi-asserted-by":"publisher","first-page":"060501","DOI":"10.35848\/1347-4065\/ab8d4f","article-title":"Physical reservoir computing: An introductory perspective","volume":"59","author":"Nakajima","year":"2020","journal-title":"Japanese Journal of Applied Physics"},{"key":"2026101621153175900_bib25","doi-asserted-by":"publisher","first-page":"2208","DOI":"10.1038\/s41467-017-01827-3","article-title":"Supervised learning in spiking neural networks with FORCE training","volume":"8","author":"Nicola","year":"2017","journal-title":"Nature Communications"},{"key":"2026101621153175900_bib26","doi-asserted-by":"publisher","first-page":"024102","DOI":"10.1103\/PhysRevLett.120.024102","article-title":"Model-free prediction of large spatiotemporally chaotic systems from data: A reservoir computing approach","volume":"120","author":"Pathak","year":"2018","journal-title":"Physical Review Letters"},{"issue":"13","key":"2026101621153175900_bib27","doi-asserted-by":"publisher","first-page":"5419","DOI":"10.1073\/pnas.1016051108","article-title":"A synaptic organizing principle for cortical neuronal groups","volume":"108","author":"Perin","year":"2011","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1","key":"2026101621153175900_bib28","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/TNN.2010.2089641","article-title":"Minimum complexity echo state network","volume":"22","author":"Rodan","year":"2011","journal-title":"IEEE Transactions on Neural Networks"},{"key":"2026101621153175900_bib29","doi-asserted-by":"publisher","first-page":"e37349","DOI":"10.7554\/eLife.37349","article-title":"Sparse recurrent excitatory connectivity in the microcircuit of the adult mouse and human cortex","volume":"7","author":"Seeman","year":"2018","journal-title":"eLife"},{"issue":"3","key":"2026101621153175900_bib30","doi-asserted-by":"publisher","first-page":"e68","DOI":"10.1371\/journal.pbio.0030068","article-title":"Highly nonrandom features of synaptic connectivity in local cortical circuits","volume":"3","author":"Song","year":"2005","journal-title":"PLOS Biology"},{"issue":"4","key":"2026101621153175900_bib31","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.neuron.2009.07.018","article-title":"Generating coherent patterns of activity from chaotic neural networks","volume":"63","author":"Sussillo","year":"2009","journal-title":"Neuron"},{"key":"2026101621153175900_bib32","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.neunet.2019.03.005","article-title":"Recent advances in physical reservoir computing: A review","volume":"115","author":"Tanaka","year":"2019","journal-title":"Neural Networks"},{"issue":"5","key":"2026101621153175900_bib33","doi-asserted-by":"publisher","first-page":"e2558","DOI":"10.1002\/nla.2558","article-title":"A split preconditioning scheme for nonlinear underdetermined least-squares problems","volume":"31","author":"Vater","year":"2024","journal-title":"Numerical Linear Algebra with Applications"},{"issue":"3","key":"2026101621153175900_bib34","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.neunet.2007.04.003","article-title":"An experimental unification of reservoir computing methods","volume":"20","author":"Verstraeten","year":"2007","journal-title":"Neural Networks"},{"key":"2026101621153175900_bib35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2012.07.005","article-title":"Re-visiting the echo state property","volume":"35","author":"Yildiz","year":"2012","journal-title":"Neural Networks"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/38\/11\/1982\/2629788\/neco.a.1578.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/38\/11\/1982\/2629788\/neco.a.1578.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T01:15:37Z","timestamp":1792199737000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/38\/11\/1982\/139099\/A-Geometry-Aware-Bio-Inspired-Sparse-Reservoir"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,16]]},"references-count":35,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,10,16]]},"published-print":{"date-parts":[[2026,10,16]]}},"URL":"https:\/\/doi.org\/10.1162\/neco.a.1578","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,11]]},"published":{"date-parts":[[2026,10,16]]}}}