{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:04:57Z","timestamp":1782363897706,"version":"3.54.5"},"reference-count":57,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T00:00:00Z","timestamp":1632182400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T00:00:00Z","timestamp":1632182400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"crossref","award":["FETOPEN-737071"],"award-info":[{"award-number":["FETOPEN-737071"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>In this work we demonstrate the use of neural networks for rapid extraction of signal parameters of discretely sampled signals. In particular, we use dense autoencoder networks to extract the parameters of interest from exponentially decaying signals and decaying oscillations. By using a three-stage training method and careful choice of the neural network size, we are able to retrieve the relevant signal parameters directly from the latent space of the autoencoder network at significantly improved rates compared to traditional algorithmic signal-analysis approaches. We show that the achievable precision and accuracy of this method of analysis is similar to conventional algorithm-based signal analysis methods, by demonstrating that the extracted signal parameters are approaching their fundamental parameter estimation limit as provided by the Cram\u00e9r\u2013Rao bound. Furthermore, we demonstrate that autoencoder networks are able to achieve signal analysis, and, hence, parameter extraction, at rates of 75 kHz, orders-of-magnitude faster than conventional techniques with similar precision. Finally, our exploration of the limitations of our approach in different computational systems suggests that analysis rates of <jats:inline-formula>\n                     <jats:tex-math\/>\n                     <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mo>&gt;<\/mml:mo>\n                     <\/mml:math>\n                     <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"mlstac1eeaieqn1.gif\" xlink:type=\"simple\"\/>\n                  <\/jats:inline-formula>200 kHz are feasible using neural networks in systems where the transfer time between the data-acquisition system and data-analysis modules can be kept below \u223c3 <jats:italic>\u00b5<\/jats:italic>s.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac1eea","type":"journal-article","created":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T22:27:22Z","timestamp":1629325642000},"page":"045024","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Rapid parameter estimation of discrete decaying signals using autoencoder networks"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5955-4858","authenticated-orcid":false,"given":"Jim C","family":"Visschers","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-4814","authenticated-orcid":false,"given":"Dmitry","family":"Budker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8050-1141","authenticated-orcid":false,"given":"Lykourgos","family":"Bougas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2021,9,21]]},"reference":[{"key":"mlstac1eeabib1","author":"Bishop","year":"1995"},{"key":"mlstac1eeabib2","author":"Hertz","year":"2018"},{"key":"mlstac1eeabib3","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1007\/978-3-030-58610-2_42","article-title":"Flow-edge guided video completion","author":"Gao","year":"2020"},{"key":"mlstac1eeabib4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3388769.3407498","article-title":"Intelligent tools for creative graphics","author":"Shamir","year":"2020"},{"key":"mlstac1eeabib5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"mlstac1eeabib6","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.91.045002","article-title":"Machine learning and the physical sciences","volume":"91","author":"Carleo","year":"2019","journal-title":"Rev. Mod. Phys."},{"key":"mlstac1eeabib7","first-page":"8459","article-title":"Learning to simulate complex physics with graph networks","author":"Sanchez-Gonzalez","year":"2020"},{"key":"mlstac1eeabib8","doi-asserted-by":"publisher","first-page":"eaar4206","DOI":"10.1126\/sciadv.aar4206","article-title":"Nanophotonic particle simulation and inverse design using artificial neural networks","volume":"4","author":"Peurifoy","year":"2018","journal-title":"Science Advances"},{"key":"mlstac1eeabib9","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1080\/00032719.2017.1340949","article-title":"Classification of chinese herbal medicine by laser-induced breakdown spectroscopy with principal component analysis and artificial neural network","volume":"51","author":"Wang","year":"2018","journal-title":"Anal. Lett."},{"key":"mlstac1eeabib10","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1016\/j.jfoodeng.2008.07.027","article-title":"Duroc and iberian pork neural network classification by visible and near infrared reflectance spectroscopy","volume":"90","author":"Del Moral","year":"2009","journal-title":"J. Food Eng."},{"key":"mlstac1eeabib11","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1046\/j.0022-202X.2004.22208.x","article-title":"Melanoma diagnosis by raman spectroscopy and neural networks: structure alterations in proteins and lipids in intact cancer tissue","volume":"122","author":"Gniadecka","year":"2004","journal-title":"J. Investig. Dermatol."},{"key":"mlstac1eeabib12","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/14\/09\/P09014","article-title":"Implementation of high-performance, sub-microsecond deep neural networks on FPGAs for trigger applications","volume":"14","author":"Nottbeck","year":"2019","journal-title":"J. Instrum."},{"key":"mlstac1eeabib13","doi-asserted-by":"publisher","DOI":"10.1177\/2053951715622512","article-title":"How the machine \u2018thinks\u2019: understanding opacity in machine learning algorithms","volume":"3","author":"Burrell","year":"2016","journal-title":"Big Data Soc."},{"key":"mlstac1eeabib14","author":"G\u00fcnther","year":"2013"},{"key":"mlstac1eeabib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.94.123001","article-title":"NMR detection with an atomic magnetometer","volume":"94","author":"Savukov","year":"2005","journal-title":"Phys. Rev. Lett."},{"key":"mlstac1eeabib16","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1140\/epjd\/e2010-00044-5","article-title":"Ultra-sensitive magnetometry based on free precession of nuclear spins","volume":"57","author":"Gemmel","year":"2010","journal-title":"Eur. Phys. J. D"},{"key":"mlstac1eeabib17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1140\/epjd\/e2014-50401-3","article-title":"Ultrasensitive 3He magnetometer for measurements of high magnetic fields","volume":"68","author":"Nikiel","year":"2014","journal-title":"Eur. Phys. J. D"},{"key":"mlstac1eeabib18","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1140\/epjd\/e2015-50875-3","article-title":"A sensitive and accurate atomic magnetometer based on free spin precession","volume":"69","author":"Gruji\u0107","year":"2015","journal-title":"Eur. Phys. J. D"},{"key":"mlstac1eeabib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.10.014002","article-title":"Free-induction-decay magnetometer based on a microfabricated Cs vapor cell","volume":"10","author":"Hunter","year":"2018","journal-title":"Phys. Rev. Appl."},{"key":"mlstac1eeabib20","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1039\/a707686j","article-title":"Cavity ring-down spectroscopy","volume":"94","author":"Wheeler","year":"1998","journal-title":"J. Chem. Soc., Faraday Trans."},{"key":"mlstac1eeabib21","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/S0009-2614(96)01351-6","article-title":"CW cavity ring down spectroscopy","volume":"264","author":"Romanini","year":"1997","journal-title":"Chem. Phys. Lett."},{"key":"mlstac1eeabib22","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1080\/014423500750040627","article-title":"Cavity ring-down spectroscopy: experimental schemes and applications","volume":"19","author":"Berden","year":"2000","journal-title":"Int. Rev. Phys. Chem."},{"key":"mlstac1eeabib23","author":"Berden","year":"2009"},{"key":"mlstac1eeabib24","doi-asserted-by":"publisher","first-page":"3223","DOI":"10.5194\/amt-12-3223-2019","article-title":"Simultaneous measurement of NO and NO2 by a dual-channel cavity ring-down spectroscopy technique","volume":"12","author":"Zhiyan","year":"2019","journal-title":"Atmos. Meas. Tech."},{"key":"mlstac1eeabib25","doi-asserted-by":"publisher","first-page":"5959","DOI":"10.1021\/jp000705n","article-title":"Cavity ring-down polarimetry (CRDP): a new scheme for probing circular birefringence and circular dichroism in the gas phase","volume":"104","author":"M\u00fcller","year":"2000","journal-title":"J. Phys. Chem. A"},{"key":"mlstac1eeabib26","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1364\/JOSAB.19.000125","article-title":"Cavity ring-down polarimetry (CRDP): theoretical and experimental characterization","volume":"19","author":"M\u00fcller","year":"2002","journal-title":"J. Opt. Soc. Am. B"},{"key":"mlstac1eeabib27","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1038\/nature13680","article-title":"Evanescent-wave and ambient chiral sensing by signal-reversing cavity ringdown polarimetry","volume":"514","author":"Sofikitis","year":"2014","journal-title":"Nature"},{"key":"mlstac1eeabib28","doi-asserted-by":"publisher","first-page":"09B603_1","DOI":"10.1063\/1.4930109","article-title":"Chiral cavity ring down polarimetry: chirality and magnetometry measurements using signal reversals","volume":"143","author":"Bougas","year":"2015","journal-title":"J. Chem. Phys."},{"key":"mlstac1eeabib29","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.92.053817","article-title":"Birefringence-induced frequency beating in high-finesse cavities by continuous-wave cavity ring-down spectroscopy","volume":"92","author":"Dupr\u00e9","year":"2015","journal-title":"Phys. Rev. A"},{"key":"mlstac1eeabib30","doi-asserted-by":"publisher","DOI":"10.1063\/5.0004476","article-title":"Continuous-wave cavity ring-down polarimetry","volume":"152","author":"Visschers","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstac1eeabib31","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.108.210801","article-title":"Cavity-enhanced parity-nonconserving optical rotation in metastable Xe and Hg","volume":"108","author":"Bougas","year":"2012","journal-title":"Phys. Rev. Lett."},{"key":"mlstac1eeabib32","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1364\/AO.52.001086","article-title":"Monitoring adsorption and sedimentation using evanescent-wave cavity ringdown ellipsometry","volume":"52","author":"Stamataki","year":"2013","journal-title":"Appl. Opt."},{"key":"mlstac1eeabib33","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1364\/OL.38.001224","article-title":"Sensitivity enhancement for evanescent-wave sensing using cavity-ring-down ellipsometry","volume":"38","author":"Sofikitis","year":"2013","journal-title":"Opt. Lett."},{"key":"mlstac1eeabib34","doi-asserted-by":"publisher","first-page":"5861","DOI":"10.1364\/AO.54.005861","article-title":"Microsecond-resolved SDR-based cavity ring down ellipsometry","volume":"54","author":"Sofikitis","year":"2015","journal-title":"Appl. Opt."},{"key":"mlstac1eeabib35","doi-asserted-by":"publisher","first-page":"2187","DOI":"10.1063\/1.1711189","article-title":"Fast exponential fitting algorithm for real-time instrumental use","volume":"75","author":"Halmer","year":"2004","journal-title":"Rev. Sci. Instrum."},{"key":"mlstac1eeabib36","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/s00340-005-1834-1","article-title":"Fast Fourier transform analysis in cavity ring-down spectroscopy: application to an optical detector for atmospheric NO2","volume":"81","author":"Mazurenka","year":"2005","journal-title":"Appl. Phys. B"},{"key":"mlstac1eeabib37","doi-asserted-by":"publisher","DOI":"10.1063\/1.2839918","article-title":"Discrete sums for the rapid determination of exponential decay constants","volume":"79","author":"Everest","year":"2008","journal-title":"Rev. Sci. Instrum."},{"key":"mlstac1eeabib38","doi-asserted-by":"publisher","DOI":"10.1063\/1.4916709","article-title":"The discrete fourier transform algorithm for determining decay constants\u2014implementation using a field programmable gate array","volume":"86","author":"Bostrom","year":"2015","journal-title":"Rev. Sci. Instrum."},{"key":"mlstac1eeabib39","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1109\/TSP.2009.2031299","article-title":"Estimation of the frequency and decay factor of a decaying exponential in noise","volume":"58","author":"Aboutanios","year":"2009","journal-title":"IEEE Trans. Signal Process."},{"key":"mlstac1eeabib40","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MIM.2011.5735249","article-title":"Estimating the parameters of sinusoids and decaying sinusoids in noise","volume":"14","author":"Aboutanios","year":"2011","journal-title":"IEEE Instrum. Meas. Mag."},{"key":"mlstac1eeabib41","doi-asserted-by":"publisher","first-page":"6863","DOI":"10.1364\/OE.411972","article-title":"Rapid parameter determination of discrete damped sinusoidal oscillations","volume":"29","author":"Visschers","year":"2021","journal-title":"Opt. Express"},{"key":"mlstac1eeabib42","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3390\/proceedings2020047009","article-title":"The neural network zoo","volume":"47","author":"van Veen","year":"2020","journal-title":"Proceedings"},{"key":"mlstac1eeabib43","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/BF00332918","article-title":"Auto-association by multilayer perceptrons and singular value decomposition","volume":"59","author":"Bourlard","year":"1988","journal-title":"Biol. Cybern."},{"key":"mlstac1eeabib44","first-page":"580","article-title":"Non-linear dimensionality reduction","volume":"5","author":"DeMers","year":"1993"},{"key":"mlstac1eeabib45","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"key":"mlstac1eeabib46","article-title":"Lossy image compression with compressive autoencoders","author":"Theis","year":"2017"},{"key":"mlstac1eeabib47","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","volume":"vol 2013","author":"Lu","year":"2013"},{"key":"mlstac1eeabib48","author":"Andrew","year":"2011"},{"key":"mlstac1eeabib49","doi-asserted-by":"publisher","first-page":"199440","DOI":"10.1109\/ACCESS.2020.3034828","article-title":"Balancing reconstruction error and Kullback-Leibler divergence in variational autoencoders","volume":"8","author":"Asperti","year":"2020","journal-title":"IEEE Access"},{"key":"mlstac1eeabib50","volume":"vol 179","author":"Gagliardi","year":"2014"},{"key":"mlstac1eeabib51","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1021\/ac062160k","article-title":"Fluorescence lifetime standards for time and frequency domain fluorescence spectroscopy","volume":"79","author":"Boens","year":"2007","journal-title":"Anal. Chem."},{"key":"mlstac1eeabib52","volume":"vol 69","author":"Cundall","year":"2013"},{"key":"mlstac1eeabib53","doi-asserted-by":"publisher","DOI":"10.1016\/j.cplett.2020.137345","article-title":"Optical activity of lysozyme in solution at 532 nm via signal-reversing cavity ring-down polarimetry","volume":"747","author":"Spiliotis","year":"2020","journal-title":"Chem. Phys. Lett."},{"key":"mlstac1eeabib54","article-title":"Development of cavity ring-down ellipsometry with spectral and submicrosecond time resolution","volume":"vol 8105","author":"Papadakis","year":"2011"},{"key":"mlstac1eeabib55","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1109\/78.376840","article-title":"Cram\u00e9r\u2013Rao lower bounds for a damped sinusoidal process","volume":"43","author":"Yao","year":"1995","journal-title":"IEEE Trans. Signal Process."},{"key":"mlstac1eeabib56","article-title":"Keras","author":"Chollet","year":"2015"},{"key":"mlstac1eeabib57","doi-asserted-by":"publisher","first-page":"1673","DOI":"10.1364\/OE.14.001673","article-title":"Ultra-sensitive ethylene post-harvest monitor based on cavity ring-down spectroscopy","volume":"14","author":"Wahl","year":"2006","journal-title":"Opt. Express"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1eea","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1eea\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1eea","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1eea\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1eea\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1eea\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1eea\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1eea\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T17:05:34Z","timestamp":1639415134000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1eea"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,21]]},"references-count":57,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,9,21]]},"published-print":{"date-parts":[[2021,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac1eea","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,21]]},"assertion":[{"value":"Rapid parameter estimation of discrete decaying signals using autoencoder networks","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2021-06-29","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-08-18","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-09-21","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}