{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T14:43:51Z","timestamp":1774277031660,"version":"3.50.1"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01-EB026955"],"award-info":[{"award-number":["R01-EB026955"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010665","name":"European Union\u2019s Horizon 2020 Research and Innovation Program within the Marie Sk\u0142odowska\u2013Curie","doi-asserted-by":"publisher","award":["839179"],"award-info":[{"award-number":["839179"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Defense Advanced Research Projects Agency\u2019s (DARPA) VIP (Super-HD Project) and AIE (HyDDENN Project) Programs"},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-19-1-0241"],"award-info":[{"award-number":["FA9550-19-1-0241"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Intel\u2019s THWAI Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tnnls.2023.3237381","type":"journal-article","created":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T18:49:08Z","timestamp":1675709348000},"page":"9885-9899","source":"Crossref","is-referenced-by-count":17,"title":["Perceptron Theory Can Predict the Accuracy of Neural Networks"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6032-6155","authenticated-orcid":false,"given":"Denis","family":"Kleyko","sequence":"first","affiliation":[{"name":"Redwood Center for Theoretical Neuroscience, University of California at Berkeley, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4371-5925","authenticated-orcid":false,"given":"Antonello","family":"Rosato","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Electronics and Telecommunications, University of Rome “La Sapienza”, Rome, Italy"}]},{"given":"Edward Paxon","family":"Frady","sequence":"additional","affiliation":[{"name":"Neuromorphic Computing Laboratory, Intel Labs, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9876-1494","authenticated-orcid":false,"given":"Massimo","family":"Panella","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Electronics and Telecommunications, University of Rome “La Sapienza”, Rome, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6738-9263","authenticated-orcid":false,"given":"Friedrich T.","family":"Sommer","sequence":"additional","affiliation":[{"name":"Redwood Center for Theoretical Neuroscience, University of California at Berkeley, Berkeley, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.9785\/cri-2019-200402"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-016-0685-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2015509117"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref5","article-title":"Opening the black box of deep neural networks via information","volume-title":"arXiv:1703.00810","author":"Shwartz-Ziv","year":"2017"},{"key":"ref6","article-title":"On the opportunities and risks of foundation models","volume-title":"arXiv:2108.07258","author":"Bommasani","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0933-3657(94)90002-7"},{"key":"ref8","article-title":"Predicting neural network accuracy from weights","volume-title":"arXiv:2002.11448","author":"Unterthiner","year":"2020"},{"key":"ref9","first-page":"1","article-title":"Predicting the accuracy of neural networks from final and intermediate layer outputs","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"DeChant"},{"key":"ref10","volume-title":"Long short-term memory in echo state networks: Details of a simulation study","author":"Jaeger","year":"2012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01084"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(01)00127-7"},{"issue":"6","key":"ref13","first-page":"1803","article-title":"How to explain individual classification decisions","volume":"11","author":"Baehrens","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","article-title":"Peephole: Predicting network performance before training","volume-title":"arXiv:1712.03351","author":"Deng","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013927"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref17","first-page":"1","article-title":"Accelerating neural architecture search using performance prediction","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Baker"},{"key":"ref18","article-title":"FitNets: Hints for thin deep nets","volume-title":"arXiv:1412.6550","author":"Romero","year":"2014"},{"key":"ref19","first-page":"10296","article-title":"Improving simple models with confidence profiles","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Dhurandhar"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.10.011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-24025-8"},{"key":"ref23","first-page":"1","article-title":"Fix your classifier: The marginal value of training the last weight layer","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hoffer"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01141"},{"key":"ref25","first-page":"1","article-title":"Zero-cost proxies for lightweight NAS","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Abdelfattah"},{"key":"ref26","first-page":"7588","article-title":"Neural architecture search without training","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Mellor"},{"key":"ref27","first-page":"1","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lee"},{"key":"ref28","first-page":"1","article-title":"BlockSwap: Fisher-guided block substitution for network compression on a budget","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Turner"},{"key":"ref29","first-page":"1","article-title":"Picking winning tickets before training by preserving gradient flow","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref30","first-page":"6377","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Tanaka"},{"key":"ref31","volume-title":"The perceptron\u2014A perceiving and recognizing automaton","author":"Rosenblatt","year":"1957"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21236\/AD0256582"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/PGEC.1963.263588"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-491850-4.50009-x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90021-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300014827"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1954.1057460"},{"key":"ref38","volume-title":"Perceptrons: An Introduction to Computational Geometry","author":"Minsky","year":"1969"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2014.07.035"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-009-9009-8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/72.377968"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3538531"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3538531"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3209104"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1615\/JAutomatInfScien.v37.i6.20"},{"key":"ref46","article-title":"Computing on functions using randomized vector representations","volume-title":"arXiv:2109.03429","author":"Paxon Frady","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3517343.3522597"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2871163"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2814400"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2020.2988388"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/72.377968"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1080\/03610918008812164"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2017.2705051"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00467"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2535338"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/69.917565"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3105949"},{"key":"ref58","first-page":"593","article-title":"Adaptive nonlinear system identification with echo state networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Jaeger"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1007\/978-3-642-35289-8_36","article-title":"A practical guide to applying echo state networks","volume-title":"Neural Networks: Tricks of the Trade","volume":"7700","author":"Luko\u0161evi\u010deus","year":"2012"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/72.471375"},{"key":"ref61","volume-title":"UCI machine learning repository","author":"Dua","year":"2017"},{"key":"ref62","first-page":"3133","article-title":"Do we need hundreds of classifiers to solve real world classification problems?","volume":"15","author":"Fernandez-Delgado","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015971"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1998.682270"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.09.001"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2462721"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.07.404"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2840128"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533316"},{"key":"ref70","article-title":"Computing with hypervectors for efficient speaker identification","volume-title":"arXiv:2208.13285","author":"Huang","year":"2022"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref72","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Krizhevsky"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3043309"},{"issue":"5","key":"ref84","first-page":"435","article-title":"Machine learning using cellular automata based feature expansion and reservoir computing","volume":"10","author":"Yilmaz","year":"2015","journal-title":"J. Cellular Automata"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00787"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966151"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63940-6_13"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3314326"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3119543"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1186\/s40708-022-00162-8"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1186\/s40708-021-00138-0"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01590"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1080\/09528130410001712862"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8640.2011.00423.x"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2017.8216554"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04397-1"},{"key":"ref97","first-page":"1","article-title":"The hyperdimensional stack machine","volume-title":"Proc. Cogn. Comput.","author":"Yerxa"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.11591\/eei.v9i3.1720"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.07.421"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-52289-0_21"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892462"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34976-8_15"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422472"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892243"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2009.03.005"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.03.005"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10589508\/10036478.pdf?arnumber=10036478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T06:11:02Z","timestamp":1721283062000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10036478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":106,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3237381","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}