{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T07:39:46Z","timestamp":1777621186110,"version":"3.51.4"},"reference-count":66,"publisher":"MIT Press","issue":"10","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2016,10]]},"abstract":"<jats:p>Neuromorphic engineering combines the architectural and computational principles of systems neuroscience with semiconductor electronics, with the aim of building efficient and compact devices that mimic the synaptic and neural machinery of the brain. The energy consumptions promised by neuromorphic engineering are extremely low, comparable to those of the nervous system. Until now, however, the neuromorphic approach has been restricted to relatively simple circuits and specialized functions, thereby obfuscating a direct comparison of their energy consumption to that used by conventional von Neumann digital machines solving real-world tasks. Here we show that a recent technology developed by IBM can be leveraged to realize neuromorphic circuits that operate as classifiers of complex real-world stimuli. Specifically, we provide a set of general prescriptions to enable the practical implementation of neural architectures that compete with state-of-the-art classifiers. We also show that the energy consumption of these architectures, realized on the IBM chip, is typically two or more orders of magnitude lower than that of conventional digital machines implementing classifiers with comparable performance. Moreover, the spike-based dynamics display a trade-off between integration time and accuracy, which naturally translates into algorithms that can be flexibly deployed for either fast and approximate classifications, or more accurate classifications at the mere expense of longer running times and higher energy costs. This work finally proves that the neuromorphic approach can be efficiently used in real-world applications and has significant advantages over conventional digital devices when energy consumption is considered.<\/jats:p>","DOI":"10.1162\/neco_a_00882","type":"journal-article","created":{"date-parts":[[2016,8,24]],"date-time":"2016-08-24T15:56:58Z","timestamp":1472054218000},"page":"2011-2044","source":"Crossref","is-referenced-by-count":26,"title":["Energy-Efficient Neuromorphic Classifiers"],"prefix":"10.1162","volume":"28","author":[{"given":"Daniel","family":"Mart\u00ed","sequence":"first","affiliation":[{"name":"D\u00e9partement d\u2019\u00c9tudes Cognitives, \u00c9cole Normale Sup\u00e9rieure\u2013PSL Research University, 75005 Paris, France; Institut Nationale de la Sant\u00e9 et de la Recherche M\u00e9dicale, 75005 Paris, France; and Center for Theoretical Neuroscience, Columbia University, College of Physicians and Surgeons, New York, NY 10032, U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mattia","family":"Rigotti","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY 10598, U.S.A., and Center for Theoretical Neuroscience, Columbia University, College of Physicians and Surgeons, New York, NY 10032, U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingoo","family":"Seok","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Columbia University, New York, NY 10027, U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Fusi","sequence":"additional","affiliation":[{"name":"Center for Theoretical Neuroscience and Mortimer B. Zuckerman Mind Brain Behavior Institute, Columbia University, College of Physicians and Surgeons, New York, NY 10032, U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.5.957"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1006.001.0001"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.7.1545"},{"key":"B4","volume-title":"Advances in neural information processing systems","volume":"18","author":"Arthur J.","year":"2006"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2010.2089556"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252637"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2753-12.2013"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2014.2313565"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1145\/2024716.2024718"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130401"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2558"},{"key":"B12","first-page":"1","author":"Butko A.","year":"2012","journal-title":"Proceedings of the 2012 7th International Workshop on Reconfigurable Communication-Centric Systems-on-Chip"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"B14","first-page":"1","volume":"99","author":"Chicca E.","year":"2014","journal-title":"Proceedings of the IEEE PP"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00018"},{"key":"B16","author":"Chrysos G.","year":"2012","journal-title":"Proceedings of the 24th Hot Chips Symposium"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"issue":"223","key":"B18","volume":"7","author":"Delbruck T.","year":"2013","journal-title":"Frontiers in Neuroscience"},{"key":"B19","doi-asserted-by":"crossref","first-page":"8599","DOI":"10.1109\/ICASSP.2013.6639344","author":"Deng L.","year":"2013","journal-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1126\/science.1225266"},{"key":"B21","first-page":"109","author":"Farabet C.","year":"2011","journal-title":"Workshops"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-002-0356-8"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016601"},{"key":"B24","author":"Garey M. R.","year":"1979","journal-title":"Computers and intractability: A guide to NP-completeness"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.816345"},{"key":"B26","volume":"5","author":"Giulioni M.","year":"2011","journal-title":"Front. Neurosci."},{"key":"B27","first-page":"1319","volume":"28","author":"Goodfellow I.","year":"2013","journal-title":"ICML"},{"key":"B28","author":"Gupta S.","year":"2015","journal-title":"Deep learning with limited neural precision"},{"key":"B29","first-page":"1","author":"Han J.","year":"2013","journal-title":"Proceedings of the 18th IEEE European Test Symposium"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2013.00118"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2005.12.126"},{"issue":"113","key":"B32","volume":"10","author":"Hussain S.","year":"2016","journal-title":"Frontiers in Neuroscience"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2011.00073"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1126\/science.1091277"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5126-6"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2007.907224"},{"key":"B37","first-page":"1493","volume":"7","author":"Keerthi S. S.","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"B38","first-page":"1097","volume-title":"Advances in neural information processing systems","author":"Krizhevsky A.","year":"2012"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1038\/nphys2276"},{"key":"B40","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1145\/1273496.1273556","author":"Larochelle H.","year":"2007","journal-title":"Proceedings of the 24th International Conference on Machine Learning"},{"key":"B41","author":"Le Q.","year":"2013","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"},{"key":"B44","first-page":"2898","author":"Livi P.","year":"2009","journal-title":"Proceedings of the IEEE International Symposium on Circuits and Systems"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2014.2314776"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-1639-8"},{"key":"B47","first-page":"1","author":"Merolla P.","year":"2011","journal-title":"Proceedings of the Custom Integrated Circuits Conference"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1126\/science.1254642"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1109\/TBCAS.2008.2005781"},{"issue":"272","key":"B50","volume":"7","author":"Neftci E.","year":"2014","journal-title":"Frontiers in Neuroscience"},{"key":"B51","author":"Neftci E. O.","year":"2015","journal-title":"Unsupervised learning in synaptic sampling machines"},{"issue":"178","key":"B52","volume":"7","author":"O\u2019Connor P.","year":"2013","journal-title":"Frontiers in Neuroscience"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2013.2259038"},{"issue":"11","key":"B54","volume":"7","author":"Pfeil T.","year":"2013","journal-title":"Frontiers in Neuroscience"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2012.6292202"},{"key":"B56","first-page":"1313","volume-title":"Advances in neural information processing systems","author":"Rahimi A.","year":"2008"},{"key":"B57","first-page":"924","author":"Raiko T.","year":"2012","journal-title":"Proceedings of the Conference on AI and Statistics"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2010.5627392"},{"key":"B59","first-page":"217","author":"Sohn K.","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.34.2571"},{"key":"B61","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-77242-4","author":"Steinwart I.","year":"2008","journal-title":"Support vector machines"},{"key":"B62","first-page":"1","author":"Stromatias E.","year":"2015","journal-title":"Proceedings of the International Joint Conference on Neural Networks"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2014.06.017"},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2013.02.008"},{"key":"B65","first-page":"281","volume-title":"Advances in neural information processing systems","volume":"9","author":"Vapnik V.","year":"1997"},{"key":"B66","first-page":"577","author":"Xi S. L.","year":"2015","journal-title":"Proceedings of the 21st International Symposium on High Performance Computer Architecture"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/NECO_a_00882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T13:30:51Z","timestamp":1749562251000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/28\/10\/2011-2044\/8199"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":66,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2016,10]]}},"alternative-id":["10.1162\/NECO_a_00882"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_00882","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,10]]}}}