{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T06:38:59Z","timestamp":1775543939681,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"armasuisse Science and Technology"},{"DOI":"10.13039\/100010664","name":"EU\u2019s H2020 Programme","doi-asserted-by":"publisher","award":["732631 (OPRECOMP)"],"award-info":[{"award-number":["732631 (OPRECOMP)"]}],"id":[{"id":"10.13039\/100010664","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1109\/tcad.2021.3075420","type":"journal-article","created":{"date-parts":[[2021,4,26]],"date-time":"2021-04-26T21:36:59Z","timestamp":1619473019000},"page":"1020-1033","source":"Crossref","is-referenced-by-count":20,"title":["CUTIE: Beyond PetaOp\/s\/W Ternary DNN Inference Acceleration With Better-Than-Binary Energy Efficiency"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2762-2307","authenticated-orcid":false,"given":"Moritz","family":"Scherer","sequence":"first","affiliation":[{"name":"Department of Information Technology and Electrical Engineering, ETH Z&#x00FC;rich, Z&#x00FC;rich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8875-7611","authenticated-orcid":false,"given":"Georg","family":"Rutishauser","sequence":"additional","affiliation":[{"name":"Department of Information Technology and Electrical Engineering, ETH Z&#x00FC;rich, Z&#x00FC;rich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1767-7715","authenticated-orcid":false,"given":"Lukas","family":"Cavigelli","sequence":"additional","affiliation":[{"name":"Huawei Technologies, Zurich Research Center, Z&#x00FC;rich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8068-3806","authenticated-orcid":false,"given":"Luca","family":"Benini","sequence":"additional","affiliation":[{"name":"Department of Information Technology and Electrical Engineering, ETH Z&#x00FC;rich, Z&#x00FC;rich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref72","author":"kingma","year":"2017","journal-title":"Adam A method for stochastic optimization"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01343"},{"key":"ref70","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"collobert","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.01.010"},{"key":"ref38","author":"byerly","year":"2020","journal-title":"A Branching and Merging Convolutional Network with Homogeneous Filter Capsules"},{"key":"ref33","first-page":"62","article-title":"XNOR-Net++: Improved binary neural networks","author":"bulat","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref32","first-page":"1","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","author":"zhou","year":"2017","journal-title":"Proc ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.01.010"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406588"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093444"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00050"},{"key":"ref35","author":"zhou","year":"2016","journal-title":"DoReFa-Net Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients"},{"key":"ref34","author":"spallanzani","year":"2019","journal-title":"Additive noise annealing and approximation properties of quantized neural networks"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.23919\/VLSIC.2017.8008533"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.2018.8357068"},{"key":"ref61","first-page":"1","article-title":"Learning recurrent binary\/ternary weights","author":"ardakani","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIC.2016.7573525"},{"key":"ref28","first-page":"153","author":"moons","year":"2019","journal-title":"BINAREYE Digital and Mixed-Signal Always-On Binary Neural Network Processing"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858362"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/VLSICircuits18222.2020.9162949"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2864289"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2946771"},{"key":"ref29","first-page":"3247","article-title":"From hashing to CNNs: Training binaryweight networks via hashing","author":"hu","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2019.2906678"},{"key":"ref68","first-page":"1","article-title":"Thermometer encoding: One hot way to resist adversarial examples","author":"buckman","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2905361"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916327"},{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2016.111"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.2018.8357071"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2899730"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.2993045"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851966"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2869150"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744788"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.007"},{"key":"ref59","first-page":"248c","article-title":"A ternary based bit scalable, 8.80 TOPS\/W CNN accelerator with many-core processing-in-memory architecture with $896k synapses\/mm^{2}$","author":"okumura","year":"2019","journal-title":"Proc Symp VLSI Circuits"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS.2019.8771562"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2020.3012576"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2905654"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870353"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"ref10","first-page":"525","article-title":"XNOR-Net: Imagenet classification using binary convolutional neural networks","author":"rastegari","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref11","first-page":"4107","article-title":"Binarized neural networks","author":"hubara","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342235"},{"key":"ref12","first-page":"1","article-title":"Ternary weight networks","author":"li","year":"2016","journal-title":"Proc NIPS Workshop Efficient Methods Deep Neural Netw"},{"key":"ref13","author":"zhu","year":"2017","journal-title":"Trained ternary quantization"},{"key":"ref14","first-page":"345","article-title":"Towards accurate binary convolutional neural network","author":"lin","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966166"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107281"},{"key":"ref17","first-page":"1","article-title":"WRPN: Wide reduced-precision networks","author":"mishra","year":"2018","journal-title":"Proc ICLR"},{"key":"ref18","author":"choi","year":"2018","journal-title":"Bridging the accuracy gap for 2-bit quantized neural networks (QNN)"},{"key":"ref19","author":"andri","year":"2020","journal-title":"ChewBaccaNN A flexible 223 TOPS\/W BNN accelerator"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2017.2654506"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"ref6","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","author":"han","year":"2015","journal-title":"Proc NIPS"},{"key":"ref5","author":"han","year":"2016","journal-title":"Deep compression Compressing deep neural networks with pruning trained quantization and huffman coding"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2950093"},{"key":"ref7","author":"iandola","year":"2016","journal-title":"Squeezenet Alexnet-level accuracy with 50x fewer parameters and< 0 5 mb model size"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref9","first-page":"3123","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70096-0_41"},{"key":"ref45","author":"cavigelli","year":"2020","journal-title":"RPR Random Partition Relaxation for Training Binary and Ternary Weight Neural Networks"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01167"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00369"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/18M1166134"},{"key":"ref41","author":"kolesnikov","year":"2019","journal-title":"Big Transfer (BiT) General Visual Representation Learning"},{"key":"ref44","author":"touvron","year":"2020","journal-title":"Fixing the train-test resolution discrepancy Fixefficientnet"},{"key":"ref43","author":"darabi","year":"2018","journal-title":"BNN+ Improved binary network training"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/9737555\/09415634.pdf?arnumber=9415634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:22:57Z","timestamp":1652732577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":72,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2021.3075420","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}