{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:41:21Z","timestamp":1740123681920,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["EXC 2064\/1","project number 390727645"],"award-info":[{"award-number":["EXC 2064\/1","project number 390727645"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["BU 1335\/11-1"],"award-info":[{"award-number":["BU 1335\/11-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002345","name":"Eberhard Karls Universit\u00e4t T\u00fcbingen","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002345","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Genet Program Evolvable Mach"],"published-print":{"date-parts":[[2022,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Time series data is often composed of a multitude of individual, superimposed dynamics. We propose a novel algorithm for inferring time series compositions through evolutionary synchronization of modular networks (ESMoN). ESMoN orchestrates a set of trained dynamic modules, assuming that some of those modules\u2019 dynamics, suitably parameterized, will be present in the targeted time series. With the help of iterative co-evolution techniques, ESMoN optimizes the activities of its modules dynamically, which effectively synchronizes the system with the unfolding time series signal and distributes the dynamic subcomponents present in the time series over the respective modules. We show that ESMoN can adapt modules of different types. Moreover, it is able to precisely identify the signal components of various time series dynamics. We thus expect that ESMoN will be useful also in other domains\u2014including, for example, medical, physical, and behavioral data domains\u2014where the data is composed of known signal sources.<\/jats:p>","DOI":"10.1007\/s10710-021-09408-6","type":"journal-article","created":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T19:02:42Z","timestamp":1626894162000},"page":"7-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Inference of time series components by online co-evolution"],"prefix":"10.1007","volume":"23","author":[{"given":"Danil","family":"Koryakin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Otte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8120-8537","authenticated-orcid":false,"given":"Martin V.","family":"Butz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,21]]},"reference":[{"key":"9408_CR1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.02.015","volume":"92","author":"A Ahmadia","year":"2017","unstructured":"A. Ahmadia, J. Tani, How can a recurrent neurodynamic predictive coding model cope with fluctuation in temporal patterns? robotic experiments on imitative interaction. Neural Netw. 92, 3\u201316 (2017)","journal-title":"Neural Netw."},{"key":"9408_CR2","unstructured":"F. Azam, Biologically inspired modular neural networks. Ph.D. thesis, Virginia Polytechnic Institute (2000)"},{"issue":"2","key":"9408_CR3","first-page":"321","volume":"30","author":"S Babinec","year":"2011","unstructured":"S. Babinec, J. Pospichal, Modular echo state neural networks in time series prediction. Comput. Inform. 30(2), 321\u2013334 (2011)","journal-title":"Comput. Inform."},{"key":"9408_CR4","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/BF00571683","volume":"3","author":"S Bengio","year":"1996","unstructured":"S. Bengio, F. Fessant, D. Collobert, Use of modular architectures for time series prediction. Neural Process. Lett. 3, 101\u2013106 (1996)","journal-title":"Neural Process. Lett."},{"key":"9408_CR5","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.neunet.2012.02.003","volume":"32","author":"K Byadarhaly","year":"2012","unstructured":"K. Byadarhaly, M. Perdoor, A. Minai, A modular neural model of motor synergies. Neural Netw. 32, 96\u2013108 (2012)","journal-title":"Neural Netw."},{"key":"9408_CR6","doi-asserted-by":"crossref","unstructured":"A.X. Carvalho, M.A. Tanner, Modeling nonlinearities with mixtures-of-experts of time series models. Int. J. Math. Math. Sci. 019423 (2006)","DOI":"10.1155\/IJMMS\/2006\/19423"},{"issue":"1","key":"9408_CR7","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TEVC.2010.2059031","volume":"15","author":"S Das","year":"2011","unstructured":"S. Das, P.N. Suganthan, Differential evolution: A survey of the state-of-the-art. IEEE Trans. Evol. Comput. 15(1), 4\u201331 (2011)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"9408_CR8","first-page":"937","volume":"9","author":"F Gomez","year":"2008","unstructured":"F. Gomez, J. Schmidhuber, R. Miikkulainen, Accelerated neural evolution through cooperatively coevolved synapses. J. Mach. Learn. Res. 9, 937\u2013965 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"9408_CR9","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1109\/TCDS.2019.2925890","volume":"13","author":"C Gumbsch","year":"2019","unstructured":"C. Gumbsch, M.V. Butz, G. Martius, Autonomous identification and goal-directed invocation of event-predictive behavioral primitives. IEEE Trans. Cogn. Dev. Syst. 13(2), 298\u2013311 (2019)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"issue":"6\u20137","key":"9408_CR10","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1016\/S0893-6080(05)80155-8","volume":"7","author":"BLM Happel","year":"1994","unstructured":"B.L.M. Happel, J.M.J. Murre, The design and evolution of modular neural network architectures. Neural Netw. 7(6\u20137), 985\u20131004 (1994)","journal-title":"Neural Netw."},{"issue":"2","key":"9408_CR11","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.neunet.2009.07.004","volume":"23","author":"G Holzmann","year":"2010","unstructured":"G. Holzmann, H. Hauser, Echo state networks with filter neurons and a delay&sum readout. Neural Netw. 23(2), 244\u2013256 (2010)","journal-title":"Neural Netw."},{"key":"9408_CR12","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1080\/09540090208559328","volume":"14","author":"M H\u00fcsken","year":"2002","unstructured":"M. H\u00fcsken, C. Igel, M. Toussaint, Task-dependent evolution of modularity in neural networks. Connect. Sci. 14, 219\u2013229 (2002)","journal-title":"Connect. Sci."},{"issue":"2","key":"9408_CR13","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1207\/s15516709cog1502_2","volume":"15","author":"RA Jacobs","year":"1991","unstructured":"R.A. Jacobs, M.I. Jordan, A.G. Barto, Task decomposition through competition in a modular connectionist architecture: The what and where vision tasks. Cogn. Sci. 15(2), 219\u2013250 (1991)","journal-title":"Cogn. Sci."},{"issue":"1","key":"9408_CR14","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"R.A. Jacobs, M.I. Jordan, S.J. Nowlan, G.E. Hinton, Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"9408_CR15","unstructured":"H. Jaeger, A tutorial on training recurrent neural networks, covering bppt, rtrl, ekf and the \u201cecho state network\u201d approach. GMD Report 159, German National Research Center for Information Technology (2002)"},{"key":"9408_CR16","unstructured":"H. Jaeger, Discovering multiscale dynamical features with hierarchical echo state networks. Tech. Rep.\u00a010, Jacobs University Bremen (2007)"},{"key":"9408_CR17","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1126\/science.1091277","volume":"304","author":"H Jaeger","year":"2004","unstructured":"H. Jaeger, H. Haas, Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless telecommunication. Science 304, 78\u201380 (2004)","journal-title":"Science"},{"key":"9408_CR18","doi-asserted-by":"crossref","unstructured":"T. Jansen, R.P.Wiegand, Exploring the explorative advantage of the cooperative coevolutionary (1+1) ea. In: GECCO\u201903 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI, pp. 310\u2013321. Springer-Verlag Berlin, Heidelberg (2003)","DOI":"10.1007\/3-540-45105-6_37"},{"key":"9408_CR19","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s13324-017-0187-3","volume":"9","author":"R Kargar","year":"2017","unstructured":"R. Kargar, A. Ebadian, J. Sokol, On booth lemniscate and starlike functions. Anal. Math. Phys. 9, 143\u2013154 (2017)","journal-title":"Anal. Math. Phys."},{"key":"9408_CR20","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.neunet.2012.08.008","volume":"36","author":"D Koryakin","year":"2012","unstructured":"D. Koryakin, J. Lohmann, M.V. Butz, Balanced echo state networks. Neural Netw. 36, 35\u201345 (2012)","journal-title":"Neural Netw."},{"key":"9408_CR21","unstructured":"D. Koryakin, F. Schrodt, M.V. Butz, Ensembles of neural oscillators. In: New Challenges in Neural Computation, pp. 57\u201364 (2015)"},{"key":"9408_CR22","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1016\/j.neucom.2013.06.012","volume":"122","author":"QL Ma","year":"2013","unstructured":"Q.L. Ma, W.B. Chen, Modular state space of echo state network. Neurocomputing 122, 406\u2013417 (2013)","journal-title":"Neurocomputing"},{"issue":"4","key":"9408_CR23","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1162\/evco.1997.5.4.373","volume":"5","author":"DE Moriarty","year":"1997","unstructured":"D.E. Moriarty, R. Miikkulainen, Forming neural networks through efficient and adaptive coevolution. Evol. Comput. 5(4), 373\u2013399 (1997)","journal-title":"Evol. Comput."},{"key":"9408_CR24","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.neucom.2016.01.088","volume":"192","author":"S Otte","year":"2016","unstructured":"S. Otte, M.V. Butz, D. Koryakin, F. Becker, M. Liwicki, A. Zell, Optimizing recurrent reservoirs with neuro-evolution. Neurocomputing 192, 128\u2013138 (2016)","journal-title":"Neurocomputing"},{"issue":"11727","key":"9408_CR25","first-page":"484","volume":"2019","author":"S Otte","year":"2019","unstructured":"S. Otte, P. Rubisch, M.V. Butz, Gradient-based learning of compositional dynamics with modular rnns. Artif. Neural Netw. Mach. Learn. ICANN 2019(11727), 484\u2013496 (2019)","journal-title":"Artif. Neural Netw. Mach. Learn. ICANN"},{"key":"9408_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1103\/PhysRevLett.120.024102","volume":"120","author":"J Pathak","year":"2018","unstructured":"J. Pathak, B. Hunt, M. Girvan, Z. Lu, E. Ott, Model-free prediction of large spatiotemporally chaotic systems from data: A reservoir computing approach. Phys. Rev. Lett. 120, 1\u20135 (2018)","journal-title":"Phys. Rev. Lett."},{"key":"9408_CR27","doi-asserted-by":"crossref","unstructured":"J. Pathak, A. Wikner, R. Fussell, S. Chandra, B. Hunt, M. Girvan, E. Ott, Hybrid forecasting of chaotic processes: Using machine learning in conjunction with a knowledge-based model. Chaos Interdisciplinary J. Nonlinear Sci. 28(4). (2018)","DOI":"10.1063\/1.5028373"},{"issue":"1","key":"9408_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/106365600568086","volume":"8","author":"MA Potter","year":"2000","unstructured":"M.A. Potter, K.A. DeJong, Cooperative coevolution: An architecture for evolving coadapted subcomponents. Evol. Comput. 8(1), 1\u201329 (2000)","journal-title":"Evol. Comput."},{"key":"9408_CR29","doi-asserted-by":"crossref","unstructured":"J. Reisinger, K.O.Stanley, R. Miikkulainen, Evolving reusable neural modules. Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2004) pp. 69\u201381 (2004)","DOI":"10.1007\/978-3-540-24855-2_7"},{"key":"9408_CR30","unstructured":"G. Rudolph, Convergence of evolutionary algorithms in general search spaces. Proceedings of the IEEE Conference on Evolutionary Computation, pp. 50\u201354 (1996)"},{"issue":"3","key":"9408_CR31","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1162\/neco.2007.19.3.757","volume":"19","author":"J Schmidhuber","year":"2007","unstructured":"J. Schmidhuber, D. Wierstra, M. Gagliolo, F. Gomez, Training recurrent neural networks by evolino. Neural Comput. 19(3), 757\u2013779 (2007)","journal-title":"Neural Comput."},{"key":"9408_CR32","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neunet.2018.07.013","volume":"108","author":"A Soltoggio","year":"2018","unstructured":"A. Soltoggio, K. Stanley, S. Risi, Born to learn: The inspiration, progress, and future of evolved plastic artificial neural networks. Neural Netw. 108, 48\u201367 (2018)","journal-title":"Neural Netw."},{"key":"9408_CR33","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10107-015-0892-3","volume":"151","author":"S Wright","year":"2015","unstructured":"S. Wright, Coordinate descent algorithms. Math. Program. 151, 3\u201334 (2015)","journal-title":"Math. Program."},{"key":"9408_CR34","doi-asserted-by":"crossref","unstructured":"F. Wyffels, B. Schrauwen, Design of a central pattern generator using reservoir computing for learning human motion. In: Advanced Technologies for Enhanced Quality of Life, pp. 118\u2013122. IEEE (2009)","DOI":"10.1109\/AT-EQUAL.2009.32"},{"key":"9408_CR35","first-page":"808","volume-title":"ICANN","author":"F Wyffels","year":"2008","unstructured":"F. Wyffels, B. Schrauwen, D. Stroobandt, Stable output feedback in reservoir computing using ridge regression, in ICANN. ed. by V. Kurkova, R. Neruda, J. Koutnik (Springer, Berlin, 2008), pp. 808\u2013817"},{"issue":"3","key":"9408_CR36","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1016\/j.neunet.2007.04.014","volume":"20","author":"Y Xue","year":"2007","unstructured":"Y. Xue, L. Yang, S. Haykin, Decoupled echo state networks with lateral inhibition. Neural Netw. 20(3), 365\u2013376 (2007)","journal-title":"Neural Netw."}],"container-title":["Genetic Programming and Evolvable Machines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10710-021-09408-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10710-021-09408-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10710-021-09408-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T14:19:52Z","timestamp":1648822792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10710-021-09408-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,21]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["9408"],"URL":"https:\/\/doi.org\/10.1007\/s10710-021-09408-6","relation":{},"ISSN":["1389-2576","1573-7632"],"issn-type":[{"type":"print","value":"1389-2576"},{"type":"electronic","value":"1573-7632"}],"subject":[],"published":{"date-parts":[[2021,7,21]]},"assertion":[{"value":"23 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}