{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:18:15Z","timestamp":1782836295629,"version":"3.54.5"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3396628","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T13:33:11Z","timestamp":1715693591000},"page":"6271-6285","source":"Crossref","is-referenced-by-count":9,"title":["Hierarchical Training of Deep Neural Networks Using Early Exiting"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1372-0368","authenticated-orcid":false,"given":"Yamin","family":"Sepehri","sequence":"first","affiliation":[{"name":"Centre Suisse d’Electronique et de Microtechnique (CSEM), Neuchâtel, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedram","family":"Pad","sequence":"additional","affiliation":[{"name":"Centre Suisse d’Electronique et de Microtechnique (CSEM), Neuchâtel, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7809-9897","authenticated-orcid":false,"given":"Ahmet","family":"Caner Y\u00fcz\u00fcg\u00fcler","sequence":"additional","affiliation":[{"name":"Signal Processing Laboratory (LTS4), École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4010-714X","authenticated-orcid":false,"given":"Pascal","family":"Frossard","sequence":"additional","affiliation":[{"name":"Signal Processing Laboratory (LTS4), École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3379-6170","authenticated-orcid":false,"given":"L.","family":"Andrea Dunbar","sequence":"additional","affiliation":[{"name":"Centre Suisse d’Electronique et de Microtechnique (CSEM), Neuchâtel, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref5","article-title":"Deep learning for chest radiographs","volume-title":"Computer Aided Classification","author":"Chandola","year":"2021"},{"key":"ref6","article-title":"OpenPose: Realtime multi-person 2D pose estimation using part affinity fields","author":"Cao","year":"2018","journal-title":"arXiv:1812.08008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581275"},{"key":"ref8","volume-title":"What\u2019s the Backward-forward Flop Ratio for Neural Networks","author":"Hobbhahn","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/S0956792521000139"},{"key":"ref10","article-title":"Privacy in deep learning: A survey","author":"Mireshghallah","year":"2020","journal-title":"arXiv:2004.12254"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539293"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2947893"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2020.2994737"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.226"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS47876.2019.00069"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2021.3116597"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2018.8645013"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref20","first-page":"1","article-title":"Flexpoint: An adaptive numerical format for efficient training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"K\u00f3ster"},{"key":"ref21","article-title":"Shifted and squeezed 8-bit floating point format for low-precision training of deep neural networks","author":"Cambier","year":"2020","journal-title":"arXiv:2001.05674"},{"key":"ref22","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref23","volume-title":"Tiny ImageNet visual recognition challenge","author":"Le","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref25","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref26","volume-title":"NVIDIA Quadro K620","year":"2022"},{"key":"ref27","volume-title":"NVIDIA GeForce RTX 2080 Ti","year":"2022"},{"key":"ref28","volume-title":"Network Coverage Outlook","year":"2023"},{"key":"ref29","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv:1308.3432"},{"key":"ref30","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv:1606.06160"},{"key":"ref31","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"arXiv:2106.08295"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10530344.pdf?arnumber=10530344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:22Z","timestamp":1764959962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":31,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3396628","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}