{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T06:19:07Z","timestamp":1700806747439},"reference-count":2,"publisher":"EDP Sciences","license":[{"start":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T00:00:00Z","timestamp":1665619200000},"content-version":"vor","delay-in-days":285,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["EPJ Web Conf."],"published-print":{"date-parts":[[2022]]},"abstract":"<jats:p>Extreme learning machines (ELMs) are a versatile machine learning technique that can be seamlessly implemented with optical systems. In short, they can be described as a network of hidden neurons with random fixed weights and biases, that generate a complex behaviour in response to an input. Yet, despite the success of the physical implementations of ELMs, there is still a lack of fundamental understanding about their optical implementations. This work makes use of an optical complex media to implement an ELM and introduce an ab-initio theoretical framework to support the experimental implementation. We validate the proposed framework, in particular, by exploring the correlation between the rank of the outputs, <jats:italic><jats:bold>H<\/jats:bold><\/jats:italic>, and its generalization capability, thus shedding new light into the inner workings of optical ELMs and opening paths towards future technological implementations of similar principles.<\/jats:p>","DOI":"10.1051\/epjconf\/202226613034","type":"journal-article","created":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T08:00:25Z","timestamp":1665648025000},"page":"13034","source":"Crossref","is-referenced-by-count":2,"title":["Unravelling an optical extreme learning machine"],"prefix":"10.1051","volume":"266","author":[{"given":"Duarte","family":"Silva","sequence":"first","affiliation":[]},{"given":"Nuno A.","family":"Silva","sequence":"additional","affiliation":[]},{"given":"Tiago D.","family":"Ferreira","sequence":"additional","affiliation":[]},{"given":"Carla C.","family":"Rosa","sequence":"additional","affiliation":[]},{"given":"Ariel","family":"Guerreiro","sequence":"additional","affiliation":[]}],"member":"250","published-online":{"date-parts":[[2022,10,13]]},"reference":[{"key":"R1","doi-asserted-by":"crossref","unstructured":"Saade A.. \u201cRandom projections through multiple optical scattering: Approximating Kernels at the speed of light\u201d. IEEE International Conference on Acoustics, Speech and Signal Processing. (2016)","DOI":"10.1109\/ICASSP.2016.7472872"},{"key":"R2","unstructured":"Huang G., Zhu Q., and Siew C.. \u201cExtreme learning machine: a new learning scheme of feedforward neural networks\u201d. IEEE International Joint Conference on Neural Networks. (2016)"}],"container-title":["EPJ Web of Conferences"],"original-title":[],"link":[{"URL":"https:\/\/www.epj-conferences.org\/10.1051\/epjconf\/202226613034\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T08:15:55Z","timestamp":1665648955000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.epj-conferences.org\/10.1051\/epjconf\/202226613034"}},"subtitle":[],"editor":[{"given":"M.F.","family":"Costa","sequence":"first","affiliation":[]},{"given":"M.","family":"Flores-Arias","sequence":"additional","affiliation":[]},{"given":"G.","family":"Pauliat","sequence":"additional","affiliation":[]},{"given":"P.","family":"Segonds","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":2,"alternative-id":["epjconf_eosam2022_13034"],"URL":"https:\/\/doi.org\/10.1051\/epjconf\/202226613034","relation":{},"ISSN":["2100-014X"],"issn-type":[{"value":"2100-014X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}