{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T21:23:28Z","timestamp":1774387408453,"version":"3.50.1"},"reference-count":28,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T00:00:00Z","timestamp":1627257600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["11C9818N, G028618N, G029519N and G006020N"],"award-info":[{"award-number":["11C9818N, G028618N, G029519N and G006020N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002661","name":"Fonds De La Recherche Scientifique - FNRS","doi-asserted-by":"publisher","award":["*"],"award-info":[{"award-number":["*"]}],"id":[{"id":"10.13039\/501100002661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>We present a method to improve the performance of a reservoir computer by keeping the reservoir fixed and increasing the number of output neurons. The additional neurons are nonlinear functions, typically chosen randomly, of the reservoir neurons. We demonstrate the interest of this expanded output layer on an experimental opto-electronic system subject to slow parameter drift which results in loss of performance. We can partially recover the lost performance by using the output layer expansion. The proposed scheme allows for a trade-off between performance gains and system complexity.<\/jats:p>","DOI":"10.3390\/e23080955","type":"journal-article","created":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T22:22:46Z","timestamp":1627338166000},"page":"955","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Photonic Reservoir Computer with Output Expansion for Unsupervized Parameter Drift Compensation"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3136-7633","authenticated-orcid":false,"given":"Ja\u00ebl","family":"Pauwels","sequence":"first","affiliation":[{"name":"Laboratoire d\u2019Information Quantique, Universit\u00e9 Libre de Bruxelles, B-1050 Bruxelles, Belgium"},{"name":"Applied Physics Research Group, Vrije Universiteit Brussel, B-1050 Ixelles, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6724-2587","authenticated-orcid":false,"given":"Guy","family":"Van der Sande","sequence":"additional","affiliation":[{"name":"Applied Physics Research Group, Vrije Universiteit Brussel, B-1050 Ixelles, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6291-0646","authenticated-orcid":false,"given":"Guy","family":"Verschaffelt","sequence":"additional","affiliation":[{"name":"Applied Physics Research Group, Vrije Universiteit Brussel, B-1050 Ixelles, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4381-2485","authenticated-orcid":false,"given":"Serge","family":"Massar","sequence":"additional","affiliation":[{"name":"Laboratoire d\u2019Information Quantique, Universit\u00e9 Libre de Bruxelles, B-1050 Bruxelles, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,7,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","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 Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1126\/science.1091277","article-title":"Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication","volume":"304","author":"Jaeger","year":"2004","journal-title":"Science"},{"key":"ref_3","doi-asserted-by":"crossref","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 Netw."},{"key":"ref_4","doi-asserted-by":"crossref","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":"Nat. Commun."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1038\/srep00287","article-title":"Optoelectronic reservoir computing","volume":"2","author":"Paquot","year":"2012","journal-title":"Sci. Rep."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3241","DOI":"10.1364\/OE.20.003241","article-title":"Photonic information processing beyond Turing: An optoelectronic implementation of reservoir computing","volume":"20","author":"Larger","year":"2012","journal-title":"Opt. Express"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"22783","DOI":"10.1364\/OE.20.022783","article-title":"All-optical reservoir computing","volume":"20","author":"Duport","year":"2012","journal-title":"Opt. Express"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1364","DOI":"10.1038\/ncomms2368","article-title":"Parallel photonic information processing at gigabyte per second data rates using transient states","volume":"4","author":"Brunner","year":"2013","journal-title":"Nat. Commun."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1364\/OPTICA.2.000438","article-title":"High-performance photonic reservoir computer based on a coherently driven passive cavity","volume":"2","author":"Vinckier","year":"2015","journal-title":"Optica"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"22381","DOI":"10.1038\/srep22381","article-title":"Fully analogue photonic reservoir computer","volume":"6","author":"Duport","year":"2016","journal-title":"Sci. Rep."},{"key":"ref_11","first-page":"011015","article-title":"High-speed photonic reservoir computing using a time-delay-based architecture: Million words per second classification","volume":"7","author":"Larger","year":"2017","journal-title":"Phys. Rev. X"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"138","DOI":"10.3389\/fphy.2019.00138","article-title":"Distributed Kerr Non-linearity in a Coherent All-Optical Fiber-Ring Reservoir Computer","volume":"7","author":"Pauwels","year":"2019","journal-title":"Front. Phys."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.1109\/TNN.2011.2161771","article-title":"Parallel reservoir computing using optical amplifiers","volume":"22","author":"Vandoorne","year":"2011","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3541","DOI":"10.1038\/ncomms4541","article-title":"Experimental demonstration of reservoir computing on a silicon photonics chip","volume":"5","author":"Vandoorne","year":"2014","journal-title":"Nat. Commun."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1364\/OPTICA.5.000756","article-title":"Reinforcement learning in a large-scale photonic recurrent neural network","volume":"5","author":"Bueno","year":"2018","journal-title":"Optica"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2653","DOI":"10.1038\/s41598-018-21011-x","article-title":"Low-loss photonic reservoir computing with multimode photonic integrated circuits","volume":"8","author":"Katumba","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_17","first-page":"106890B","article-title":"Dual-mode semiconductor lasers in reservoir computing","volume":"Volume 10689","author":"Harkhoe","year":"2018","journal-title":"Neuro-Inspired Photonic Computing"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1218","DOI":"10.1364\/OL.44.001218","article-title":"Reservoir computing based on transverse modes in a single optical waveguide","volume":"44","author":"Mesaritakis","year":"2019","journal-title":"Opt. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"30349","DOI":"10.1364\/OE.399495","article-title":"Using multidimensional speckle dynamics for high-speed, large-scale, parallel photonic computing","volume":"28","author":"Sunada","year":"2020","journal-title":"Opt. Express"},{"key":"ref_20","first-page":"19","article-title":"Optical reservoir computer using speckle in a multimode waveguide","volume":"Volume 11299","author":"Jalali","year":"2020","journal-title":"AI and Optical Data Sciences"},{"key":"ref_21","first-page":"041037","article-title":"Large-scale optical reservoir computing for spatiotemporal chaotic systems prediction","volume":"10","author":"Rafayelyan","year":"2020","journal-title":"Phys. Rev. X"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1515\/nanoph-2016-0132","article-title":"Advances in photonic reservoir computing","volume":"6","author":"Brunner","year":"2017","journal-title":"Nanophotonics"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wyffels, F., Schrauwen, B., and Stroobandt, D. (2008). Stable output feedback in reservoir computing using ridge regression. International Conference on Artificial Neural Networks, Springer.","DOI":"10.1109\/IJCNN.2008.4634252"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1364\/OE.21.000012","article-title":"Optoelectronic reservoir computing: Tackling noise-induced performance degradation","volume":"21","author":"Soriano","year":"2013","journal-title":"Opt. Express"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/JSTQE.2019.2929181","article-title":"Phase noise robustness of a coherent spatially parallel optical reservoir","volume":"26","author":"Alata","year":"2019","journal-title":"IEEE J. Sel. Top. Quantum Electron."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1162\/089976602317318938","article-title":"Slow feature analysis: Unsupervised learning of invariances","volume":"14","author":"Wiskott","year":"2002","journal-title":"Neural Comput."},{"key":"ref_27","unstructured":"Jaeger, H. (2021, July 15). Short Term Memory in Echo State Networks, Available online: http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.720.3974."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1038\/srep00514","article-title":"Information processing capacity of dynamical systems","volume":"2","author":"Dambre","year":"2012","journal-title":"Sci. Rep."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/8\/955\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:35:15Z","timestamp":1760164515000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/8\/955"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,26]]},"references-count":28,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["e23080955"],"URL":"https:\/\/doi.org\/10.3390\/e23080955","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,26]]}}}