{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:06:52Z","timestamp":1740100012254,"version":"3.37.3"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T00:00:00Z","timestamp":1617753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T00:00:00Z","timestamp":1617753600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T00:00:00Z","timestamp":1617753600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,4,7]]},"DOI":"10.1109\/isqed51717.2021.9424299","type":"proceedings-article","created":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T00:09:51Z","timestamp":1620691791000},"page":"149-153","source":"Crossref","is-referenced-by-count":0,"title":["Regularization-Free Structural Pruning for GPU Inference Acceleration"],"prefix":"10.1109","author":[{"given":"Chuliang","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaodi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keyu","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xunzhao","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref31","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NIPS"},{"key":"ref30","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Tech Report"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref35","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref11","article-title":"Trained ternary quantization","author":"zhu","year":"2016","journal-title":"arXiv preprint arXiv 1612 01064"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3273957"},{"key":"ref13","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Proc NIPS"},{"key":"ref14","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"hassibi","year":"1993","journal-title":"Proc NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.241"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2957724"},{"key":"ref17","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015676"},{"key":"ref28","article-title":"Hierarchical block sparse neural networks","author":"vooturi","year":"2018","journal-title":"arXiv preprint arXiv 1808 03578"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.460"},{"key":"ref27","article-title":"Block-sparse recurrent neural networks","author":"narang","year":"2017","journal-title":"arXiv preprint arXiv 1711 07064"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1980.1102314"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298809"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2690379"},{"key":"ref7","article-title":"Compression of deep convolutional neural networks for fast and low power mobile applications","author":"kim","year":"2016","journal-title":"Proc ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2917844"},{"key":"ref9","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or ?1","author":"courbariaux","year":"2016","journal-title":"arXiv preprint arXiv 1602 02830"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref20","article-title":"Campfire: Compressible, regularization-free, structured sparse training for hardware accelerators","author":"gamboa","year":"2020","journal-title":"arXiv preprint arXiv 2001 04786"},{"key":"ref22","first-page":"1","article-title":"Optimally approximated and unbiased floating-point multiplier with runtime configurability","author":"chen","year":"2020","journal-title":"ICCAD"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref24","article-title":"A systematic DNN weight pruning framework using alternating direction method of multipliers","author":"zhang","year":"2018","journal-title":"Proc ECCV"},{"key":"ref23","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc NIPS"},{"key":"ref26","article-title":"Progressive weight pruning of deep neural networks using ADMM","author":"ye","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref25","article-title":"StructADMM: A systematic, high-efficiency framework of structured weight pruning for DNNs","author":"zhang","year":"2018","journal-title":"arXiv preprint arXiv 1807 11091"}],"event":{"name":"2021 22nd International Symposium on Quality Electronic Design (ISQED)","start":{"date-parts":[[2021,4,7]]},"location":"Santa Clara, CA, USA","end":{"date-parts":[[2021,4,9]]}},"container-title":["2021 22nd International Symposium on Quality Electronic Design (ISQED)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424228\/9424248\/09424299.pdf?arnumber=9424299","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:24Z","timestamp":1652197284000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9424299\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,7]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/isqed51717.2021.9424299","relation":{},"subject":[],"published":{"date-parts":[[2021,4,7]]}}}