{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T06:13:44Z","timestamp":1777875224488,"version":"3.51.4"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100018703","name":"European Innovation Council","doi-asserted-by":"publisher","award":["101070918"],"award-info":[{"award-number":["101070918"]}],"id":[{"id":"10.13039\/100018703","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["M4C1 CUP I53D23003600006"],"award-info":[{"award-number":["M4C1 CUP I53D23003600006"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["20229JRTZA"],"award-info":[{"award-number":["20229JRTZA"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100024370","name":"Ministero dell'Istruzione dell'Universita e della Ricerca","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100024370","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.neucom.2026.132952","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T00:23:09Z","timestamp":1770164589000},"page":"132952","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Sparse assemblies of recurrent neural networks with stability guarantees"],"prefix":"10.1016","volume":"675","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5084-0505","authenticated-orcid":false,"given":"Andrea","family":"Ceni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valerio","family":"De Caro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davide","family":"Bacciu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudio","family":"Gallicchio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.132952_bib0005","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"nature"},{"key":"10.1016\/j.neucom.2026.132952_bib0010","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"10.1016\/j.neucom.2026.132952_bib0015","author":"Pascanu"},{"key":"10.1016\/j.neucom.2026.132952_bib0020","first-page":"10456","article-title":"Stable and expressive recurrent vision models","volume":"33","author":"Linsley","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.132952_bib0025","series-title":"International Conference on Learning Representations","article-title":"Stable recurrent models","author":"Miller","year":"2019"},{"key":"10.1016\/j.neucom.2026.132952_bib0030","first-page":"13","article-title":"The \u201cecho state\u201d approach to analysing and training recurrent neural networks-with an erratum note","volume":"148","author":"Jaeger","year":"2001"},{"key":"10.1016\/j.neucom.2026.132952_bib0035","series-title":"International Conference on Learning Representations","article-title":"Can recurrent neural networks warp time?","author":"Tallec","year":"2018"},{"key":"10.1016\/j.neucom.2026.132952_bib0040","article-title":"Learning stable deep dynamics models","volume":"32","author":"Kolter","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.132952_bib0045","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1016\/S0005-1098(98)00019-3","article-title":"On contraction analysis for non-linear systems","volume":"34","author":"Lohmiller","year":"1998","journal-title":"Automatica"},{"key":"10.1016\/j.neucom.2026.132952_bib0050","article-title":"Stable architectures for deep neural networks","volume":"34","author":"Haber","year":"2017","journal-title":"Inverse Problems"},{"key":"10.1016\/j.neucom.2026.132952_bib0055","author":"Chang"},{"key":"10.1016\/j.neucom.2026.132952_bib0060","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Anti-symmetric dgn: a stable architecture for deep graph networks","author":"Gravina","year":"2022"},{"key":"10.1016\/j.neucom.2026.132952_bib0065","series-title":"Proceedings of the 41st International Conference on Machine Learning","article-title":"Long range propagation on continuous-time dynamic graphs","author":"Gravina","year":"2024"},{"key":"10.1016\/j.neucom.2026.132952_bib0070","first-page":"30512","article-title":"RNNS of RNNS: recursive construction of stable assemblies of recurrent neural networks","volume":"35","author":"Kozachkov","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.132952_bib0075","doi-asserted-by":"crossref","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":"10.1016\/j.neucom.2026.132952_bib0080","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0006-3495(72)86068-5","article-title":"Excitatory and inhibitory interactions in localized populations of model neurons","volume":"12","author":"Wilson","year":"1972","journal-title":"Biophys. J."},{"key":"10.1016\/j.neucom.2026.132952_bib0085","article-title":"Input-output equivalence of unitary and contractive RNNS","volume":"32","author":"Emami","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.132952_bib0090","doi-asserted-by":"crossref","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 netw."},{"key":"10.1016\/j.neucom.2026.132952_bib0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.physd.2020.132609","article-title":"The echo index and multistability in input-driven recurrent neural networks","volume":"412","author":"Ceni","year":"2020","journal-title":"Phys. D"},{"key":"10.1016\/j.neucom.2026.132952_bib0100","article-title":"Fastgrnn: a fast, accurate, stable and tiny kilobyte sized gated recurrent neural network","volume":"31","author":"Kusupati","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.132952_bib0105","series-title":"International Workshop on Ambient Assisted Living","first-page":"216","article-title":"Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine","author":"Anguita","year":"2012"},{"key":"10.1016\/j.neucom.2026.132952_bib0110","author":"Le"},{"key":"10.1016\/j.neucom.2026.132952_bib0115","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"key":"10.1016\/j.neucom.2026.132952_bib0120","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1162\/NECO_a_00221","article-title":"Mathematical equivalence of two common forms of firing rate models of neural networks","volume":"24","author":"Miller","year":"2012","journal-title":"Neural Comput."},{"key":"10.1016\/j.neucom.2026.132952_bib0125","doi-asserted-by":"crossref","first-page":"517","DOI":"10.3390\/info15090517","article-title":"Recurrent neural networks: a comprehensive review of architectures, variants, and applications","volume":"15","author":"Mienye","year":"2024","journal-title":"Information"},{"key":"10.1016\/j.neucom.2026.132952_bib0130","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/j.neucom.2026.132952_bib0135","series-title":"Towards adaptive and stable compositional assemblies of recurrent neural network modules","author":"De Caro","year":"2025"},{"key":"10.1016\/j.neucom.2026.132952_bib0140","series-title":"International Conference on Machine Learning","first-page":"5806","article-title":"Stabilizing gradients for deep neural networks via efficient SVD parameterization","author":"Zhang","year":"2018"},{"issue":"6","key":"10.1016\/j.neucom.2026.132952_bib0145","doi-asserted-by":"crossref","first-page":"10794","DOI":"10.1109\/TNNLS.2025.3538924","article-title":"Random orthogonal additive filters: a solution to the vanishing\/exploding gradient of deep neural networks","volume":"36","author":"Ceni","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.132952_bib0150","series-title":"2017 International Joint Conference on Neural Networks (IJCNN)","first-page":"1578","article-title":"Time series classification from scratch with deep neural networks: a strong baseline","author":"Wang","year":"2017"},{"key":"10.1016\/j.neucom.2026.132952_bib0155","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1007\/s10618-019-00619-1","article-title":"Deep learning for time series classification: a review","volume":"33","author":"Ismail Fawaz","year":"2019","journal-title":"Data Min. Knowl. Discov."},{"key":"10.1016\/j.neucom.2026.132952_bib0160","doi-asserted-by":"crossref","first-page":"1032","DOI":"10.1007\/s10618-021-00745-9","article-title":"Time series extrinsic regression: predicting numeric values from time series data","volume":"35","author":"Tan","year":"2021","journal-title":"Data Min. Knowl. Discov."},{"key":"10.1016\/j.neucom.2026.132952_bib0165","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Timesnet: temporal 2D-variation modeling for general time series analysis","author":"Wu","year":"2023"},{"key":"10.1016\/j.neucom.2026.132952_bib0170","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1007\/s10618-020-00701-z","article-title":"Rocket: exceptionally fast and accurate time series classification using random convolutional kernels","volume":"34","author":"Dempster","year":"2020","journal-title":"Data Min. Knowl. Discov."},{"key":"10.1016\/j.neucom.2026.132952_bib0175","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","article-title":"Inceptiontime: finding alexnet for time series classification","volume":"34","author":"Ismail Fawaz","year":"2020","journal-title":"Data Min. Knowl. Discov."},{"key":"10.1016\/j.neucom.2026.132952_bib0180","series-title":"International Conference on Learning Representations","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2022"},{"key":"10.1016\/j.neucom.2026.132952_bib0185","series-title":"The Twelfth International Conference on Learning Representations","article-title":"Itransformer: inverted transformers are effective for time series forecasting","author":"Liu","year":"2024"},{"key":"10.1016\/j.neucom.2026.132952_bib0190","doi-asserted-by":"crossref","first-page":"140589","DOI":"10.52202\/079017-4463","article-title":"Units: a unified multi-task time series model","volume":"37","author":"Gao","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.132952_bib0195","first-page":"43322","article-title":"One fits all: power general time series analysis by pretrained LM","volume":"36","author":"Zhou","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.132952_bib0200","series-title":"International Conference on Learning Representations","article-title":"RNNS incrementally evolving on an equilibrium manifold: a panacea for vanishing and exploding gradients?","author":"Kag","year":"2020"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226003498?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226003498?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T21:21:28Z","timestamp":1777584088000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226003498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":40,"alternative-id":["S0925231226003498"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.132952","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Sparse assemblies of recurrent neural networks with stability guarantees","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.132952","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132952"}}