{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T16:14:28Z","timestamp":1771517668822,"version":"3.50.1"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency (JST) CREST Grant Number JPMJCR18K2, Japan","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3245808","type":"journal-article","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T23:07:44Z","timestamp":1676588864000},"page":"16588-16604","source":"Crossref","is-referenced-by-count":6,"title":["Recurrent Residual Networks Contain Stronger Lottery Tickets"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3206-1479","authenticated-orcid":false,"given":"\u00c1ngel L\u00f3pez","family":"Garc\u00eda-Arias","sequence":"first","affiliation":[{"name":"Tokyo Institute of Technology, Kanagawa, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuyuki","family":"Okoshi","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Kanagawa, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0377-2108","authenticated-orcid":false,"given":"Masanori","family":"Hashimoto","sequence":"additional","affiliation":[{"name":"Department of Communications and Computer Engineering, Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1543-1252","authenticated-orcid":false,"given":"Masato","family":"Motomura","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Kanagawa, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6639-7694","authenticated-orcid":false,"given":"Jaehoon","family":"Yu","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Kanagawa, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3597","article-title":"Deconstructing lottery tickets: Zeros, signs, and the supermask","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01191"},{"key":"ref3","first-page":"1","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Repr.","author":"Frankle"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731668"},{"key":"ref5","article-title":"Plant \u2018n\u2019 seek: Can you find the winning ticket?","author":"Fischer","year":"2021","journal-title":"arXiv:2111.11153"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref8","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"key":"ref10","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref11","article-title":"Dynamic sparse training: Find efficient sparse network from scratch with trainable masked layers","author":"Liu","year":"2020","journal-title":"arXiv:2005.06870"},{"key":"ref12","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"Zhu","year":"2017","journal-title":"arXiv:1710.01878"},{"key":"ref13","article-title":"The state of sparsity in deep neural networks","author":"Gale","year":"2019","journal-title":"arXiv:1902.09574"},{"key":"ref14","article-title":"What is the state of neural network pruning?","author":"Blalock","year":"2020","journal-title":"arXiv:2003.03033"},{"key":"ref15","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. ICLR","author":"Han"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_28"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"ref18","article-title":"How many winning tickets are there in one DNN?","author":"Grosse","year":"2020","journal-title":"arXiv:2006.07014"},{"key":"ref19","first-page":"3259","article-title":"Linear mode connectivity and the lottery ticket hypothesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frankle"},{"key":"ref20","first-page":"1","article-title":"Drawing early-bird tickets: Toward more efficient training of deep networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"You"},{"key":"ref21","first-page":"1","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref22","first-page":"2943","article-title":"Rigging the lottery: Making all tickets winners","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Evci"},{"key":"ref23","first-page":"1","article-title":"A signal propagation perspective for pruning neural networks at initialization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6910"},{"key":"ref25","first-page":"1","article-title":"Picking winning tickets before training by preserving gradient flow","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref26","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":"ref27","first-page":"1","article-title":"Robust pruning at initialization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hayou"},{"key":"ref28","first-page":"1","article-title":"Pruning neural networks at initialization: Why are we missing the mark?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Frankle"},{"key":"ref29","first-page":"20838","article-title":"MEST: Accurate and fast memory-economic sparse training framework on the edge","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref30","article-title":"Rare gems: Finding lottery tickets at initialization","author":"Sreenivasan","year":"2022","journal-title":"arXiv:2202.12002"},{"key":"ref31","first-page":"6682","article-title":"Proving the lottery ticket hypothesis: Pruning is all you need","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Malach"},{"key":"ref32","first-page":"2599","article-title":"Optimal lottery tickets via subset sum: Logarithmic over-parameterization is sufficient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pensia"},{"key":"ref33","first-page":"2925","article-title":"Logarithmic pruning is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Orseau"},{"key":"ref34","first-page":"1","article-title":"Multi-Prize Lottery Ticket Hypothesis: Finding accurate binary neural networks by pruning a randomly weighted network","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Diffenderfer"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2006.875977"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.03.005"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00349"},{"key":"ref38","first-page":"1","article-title":"Training batchnorm and only batchnorm: On the expressive power of random features in CNNs","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Frankle"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_5"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27606-9"},{"key":"ref41","first-page":"3531","article-title":"Finding nearly everything within random binary networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Sreenivasan"},{"key":"ref42","article-title":"Signing the supermask: Keep, hide, invert","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Koster"},{"key":"ref43","first-page":"17045","article-title":"Multicoated supermasks enhance hidden networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Okoshi"},{"key":"ref44","first-page":"15173","article-title":"Supermasks in superposition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wortsman"},{"key":"ref45","first-page":"163","article-title":"Slot machines: Discovering winning combinations of random weights in neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Aladago"},{"key":"ref46","first-page":"4503","article-title":"Pruning randomly initialized neural networks with iterative randomization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chijiwa"},{"key":"ref47","first-page":"1","article-title":"Hidden-fold networks: Random recurrent residuals using sparse supermasks","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"L\u00f3pez Garc\u00eda-Arias"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-019-0392-5"},{"key":"ref51","first-page":"1","article-title":"Residual networks behave like ensembles of relatively shallow networks","volume":"29","author":"Veit","year":"2016","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref52","article-title":"Highway and residual networks learn unrolled iterative estimation","author":"Greff","year":"2016","journal-title":"arXiv:1612.07771"},{"key":"ref53","article-title":"Residual connections encourage iterative inference","author":"Jastrzebski","year":"2017","journal-title":"arXiv:1710.04773"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref55","article-title":"Multi-residual networks: Improving the speed and accuracy of residual networks","author":"Abdi","year":"2016","journal-title":"arXiv:1609.05672"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref57","article-title":"Visualizing residual networks","author":"Chu","year":"2017","journal-title":"arXiv:1701.02362"},{"key":"ref58","article-title":"Bridging the gaps between residual learning, recurrent neural networks and visual cortex","author":"Liao","year":"2016","journal-title":"arXiv:1604.03640"},{"key":"ref59","first-page":"82","article-title":"Recurrent convolutional neural networks for scene labeling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinheiro"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298958"},{"key":"ref61","article-title":"Loopy neural nets: Imitating feedback loops in the human brain","author":"Caswell","year":"2016"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref63","first-page":"1","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Shi"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.196"},{"key":"ref65","article-title":"Recurrent convolution for compact and cost-adjustable neural networks: An empirical study","author":"Zhang","year":"2019","journal-title":"arXiv:1902.09809"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00529"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802998"},{"key":"ref68","first-page":"7397","article-title":"Deeply shared filter bases for parameter-efficient convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kang"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2020.11.009"},{"key":"ref70","article-title":"CORnet: Modeling the neural mechanisms of core object recognition","author":"Kubilius","year":"2018","journal-title":"bioRxiv"},{"key":"ref71","article-title":"IamNN: Iterative and adaptive mobile neural network for efficient image classification","author":"Leroux","year":"2018","journal-title":"arXiv:1804.10123"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2017.01551"},{"key":"ref73","article-title":"Learning implicitly recurrent CNNs through parameter sharing","author":"Savarese","year":"2019","journal-title":"arXiv:1902.09701"},{"key":"ref74","article-title":"Brain-score: Which artificial neural network for object recognition is most brain-like?","author":"Schrimpf","year":"2020","journal-title":"bioRxiv"},{"key":"ref75","article-title":"Layer folding: Neural network depth reduction using activation linearization","author":"Ben Dror","year":"2021","journal-title":"arXiv:2106.09309"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11213603"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref79","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref80","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016","journal-title":"arXiv:1607.08022"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref84","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.01191","volume-title":"What\u2019s Hidden in a Randomly Weighted Neural Network?","author":"Ramanujan","year":"2020"},{"key":"ref85","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref87","volume-title":"Deeplearningexamples\/Pytorch\/","year":"2021"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref91","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref92","first-page":"1","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref93","article-title":"Lottery tickets with nonzero biases","author":"Fischer","year":"2021","journal-title":"arXiv:2110.11150"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00360"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897718"},{"key":"ref96","first-page":"1","article-title":"Latent weights do not exist: Rethinking binarized neural network optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Helwegen"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref98","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","volume":"34","author":"Tolstikhin"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10045676.pdf?arnumber=10045676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T16:35:25Z","timestamp":1707842125000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10045676\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3245808","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}