{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:12:36Z","timestamp":1778789556371,"version":"3.51.4"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"\u201cResearch and Development of Enhanced Infrastructures for Post 5G Information Communication Systems\u201d commissioned by the New Energy and Industrial Technology Development Organization","award":["JPNP20017"],"award-info":[{"award-number":["JPNP20017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3686628","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:50:57Z","timestamp":1776887457000},"page":"68271-68280","source":"Crossref","is-referenced-by-count":0,"title":["Fast GPU Inference With Unstructured-Pruned Sparse DNN Architectures"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3247-9565","authenticated-orcid":false,"given":"Masahiko","family":"Ando","sequence":"first","affiliation":[{"name":"Research and Development Group, Hitachi, Ltd., Kokubunji, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2382-6670","authenticated-orcid":false,"given":"Keita","family":"Yamane","sequence":"additional","affiliation":[{"name":"Research and Development Group, Hitachi, Ltd., Kokubunji, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1069-3221","authenticated-orcid":false,"given":"Takashi","family":"Oshima","sequence":"additional","affiliation":[{"name":"Research and Development Group, Hitachi, Ltd., Kokubunji, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","author":"Hoefler","year":"2021","journal-title":"arXiv:2102.00554"},{"key":"ref2","article-title":"A survey on deep neural network pruning-taxonomy, comparison, analysis, and recommendations","author":"Cheng","year":"2023","journal-title":"arXiv:2308.06767"},{"key":"ref3","first-page":"646","article-title":"Digital twin technology for continuous improvement at manufacturing sites","volume":"69","author":"Ito","year":"2020","journal-title":"Hitachi Rev."},{"key":"ref4","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2019.8916327"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2020.3043870"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/isscc49657.2024.10454357"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3377147"},{"key":"ref9","article-title":"Hardware acceleration for neural networks: A comprehensive survey","author":"Xu","year":"2025","journal-title":"arXiv:2512.23914"},{"key":"ref10","article-title":"A closer look at structured pruning for neural network compression","author":"Crowley","year":"2018","journal-title":"arXiv:1810.04622"},{"key":"ref11","article-title":"Recent advances on neural network pruning at initialization","author":"Wang","year":"2021","journal-title":"arXiv:2103.06460"},{"key":"ref12","article-title":"Pruning neural networks without any data by iteratively conserving synaptic flow","author":"Tanaka","year":"2020","journal-title":"arXiv:2006.05467"},{"key":"ref13","article-title":"Pushing the limits of sparsity: A bag of tricks for extreme pruning","author":"Li","year":"2024","journal-title":"arXiv:2411.13545"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2898"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3402326"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414654"},{"key":"ref17","volume-title":"NVIDIA TensorRT Developer Guide"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref19","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. NeurIPS","volume":"25","author":"Krizhevsky"},{"key":"ref20","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref21","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","author":"Lee","year":"2018","journal-title":"arXiv:1810.02340"},{"key":"ref22","article-title":"Progressive skeletonization: Trimming more fat from a network at initialization","author":"de Jorge","year":"2020","journal-title":"arXiv:2006.09081"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref24","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015","journal-title":"arXiv:1502.03167"},{"key":"ref25","article-title":"Explainable deep one-class classification","author":"Liznerski","year":"2020","journal-title":"arXiv:2007.01760"},{"key":"ref26","volume-title":"Jetson Nano Developer Kit"},{"key":"ref27","volume-title":"Jetson AGX Xavier"},{"key":"ref28","volume-title":"A100 Data Center GPU"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582047"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3544559"},{"key":"ref33","volume-title":"CuSPARSE Library","year":"2026"},{"key":"ref34","article-title":"Accelerating sparse deep neural networks","author":"Mishra","year":"2021","journal-title":"arXiv:2104.08378"},{"key":"ref35","volume-title":"Information processing system and neural network conversion method","author":"Ando","year":"2025"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11491919.pdf?arnumber=11491919","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:59:32Z","timestamp":1778788772000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11491919\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3686628","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}