{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T13:48:18Z","timestamp":1776088098347,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"National University of Sciences and Technology, Islamabad"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3069906","type":"journal-article","created":{"date-parts":[[2021,3,30]],"date-time":"2021-03-30T20:31:57Z","timestamp":1617136317000},"page":"53647-53668","source":"Crossref","is-referenced-by-count":3,"title":["TiQSA: Workload Minimization in Convolutional Neural Networks Using Tile Quantization and Symmetry Approximation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5322-9808","authenticated-orcid":false,"given":"Dilshad","family":"Sabir","sequence":"first","affiliation":[{"name":"Department of Computer and Software Engineering, College of Electrical and Mechanical Engineering (E&ME), National University of Sciences and Technology, Islamabad, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9841-6132","authenticated-orcid":false,"given":"Muhammmad Abdullah","family":"Hanif","sequence":"additional","affiliation":[{"name":"Institute of Computer Engineering, Technische Universit\u00e4t Wien (TU Wien), Vienna, Austria"}]},{"given":"Ali","family":"Hassan","sequence":"additional","affiliation":[{"name":"Department of Computer and Software Engineering, College of Electrical and Mechanical Engineering (E&ME), National University of Sciences and Technology, Islamabad, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0487-0703","authenticated-orcid":false,"given":"Saad","family":"Rehman","sequence":"additional","affiliation":[{"name":"Faculty of Computer Engineering, HITEC University, Taxila, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2607-8135","authenticated-orcid":false,"given":"Muhammad","family":"Shafique","sequence":"additional","affiliation":[{"name":"Division of Engineering, New York University Abu Dhabi (NYU AD), Abu Dhabi, United Arab Emirates"}]}],"member":"263","reference":[{"key":"ref39","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","volume":"abs 1511","author":"courbariaux","year":"2015","journal-title":"CoRR"},{"key":"ref38","first-page":"662","article-title":"Less is more: Towards compact CNNs","author":"zhou","year":"2016","journal-title":"Proc ECCV"},{"key":"ref33","first-page":"177","article-title":"Comparing biases for minimal network construction with back-propagation","author":"hanson","year":"1989","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","article-title":"Enabling sparse winograd convolution by native pruning","volume":"abs 1702 8597","author":"li","year":"2017","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.022"},{"key":"ref30","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"arXiv 1511 06434"},{"key":"ref37","article-title":"Fast convnets using group-wise brain damage","volume":"abs 1506 2515","author":"lebedev","year":"2015","journal-title":"CoRR"},{"key":"ref36","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015","journal-title":"arXiv 1510 00149 [cs]"},{"key":"ref35","article-title":"Compressing neural networks with the hashing trick","volume":"abs 1504 4788","author":"chen","year":"2015","journal-title":"CoRR"},{"key":"ref34","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"hassibi","year":"1993","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1026\/1\/012019"},{"key":"ref29","author":"horowitz","year":"0","journal-title":"Energy Table for 45 nm Process"},{"key":"ref2","author":"krizhevsky","year":"0","journal-title":"Cifar-10 (canadian institute for advanced research)"},{"key":"ref1","author":"lecun","year":"2010","journal-title":"MNIST Handwritten Digit Database"},{"key":"ref20","article-title":"Structured pruning of deep convolutional neural networks","volume":"abs 1512 8571","author":"anwar","year":"2015","journal-title":"CoRR"},{"key":"ref22","article-title":"Compact deep convolutional neural networks with coarse pruning","volume":"abs 1610 9639","author":"anwar","year":"2016","journal-title":"CoRR"},{"key":"ref21","article-title":"Pruning filters for efficient convnets","volume":"abs 1608 8710","author":"li","year":"2016","journal-title":"CoRR"},{"key":"ref24","article-title":"Learning both weights and connections for efficient neural networks","volume":"abs 1507 6149","author":"han","year":"2015","journal-title":"CoRR"},{"key":"ref23","article-title":"Data-free parameter pruning for deep neural networks","volume":"abs 1507 6149","author":"srinivas","year":"2015","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68612-7_69"},{"key":"ref25","article-title":"Fast algorithms for convolutional neural networks","volume":"abs 1509 9308","author":"lavin","year":"2015","journal-title":"CoRR"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451339"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICECA.2018.8474912"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"ref40","article-title":"Neural networks with few multiplications","volume":"abs 1510 3009","author":"lin","year":"2016","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3178115"},{"key":"ref13","article-title":"A non-technical survey on deep convolutional neural network architectures","volume":"abs 1803 2129","author":"altenberger","year":"2018","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.56"},{"key":"ref16","article-title":"Going deeper with convolutions","volume":"abs 1409 4842","author":"szegedy","year":"2014","journal-title":"CoRR"},{"key":"ref17","article-title":"Spatial-winograd pruning enabling sparse winograd convolution","volume":"abs 1901 2132","author":"yu","year":"2019","journal-title":"CoRR"},{"key":"ref18","article-title":"Efficient sparse-winograd convolutional neural networks","volume":"abs 1802 6367","author":"liu","year":"2018","journal-title":"CoRR"},{"key":"ref19","first-page":"1","article-title":"Pruning of winograd and FFT based convolution algorithm","author":"liu","year":"2016","journal-title":"Proc Convolutional Neural Netw Vis Recognit"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICoAC.2017.8441512"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2475625"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3234150"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2891888"},{"key":"ref49","article-title":"ShuffleNet: An extremely efficient convolutional neural network for mobile devices","author":"zhang","year":"2017","journal-title":"arXiv 1707 01083"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref46","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","volume":"abs 1708 7747","author":"xiao","year":"2017","journal-title":"CoRR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472158"},{"key":"ref48","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref47","first-page":"662","article-title":"Less is more: Towards compact CNNs","author":"zhou","year":"2016","journal-title":"Vision Computer"},{"key":"ref42","article-title":"Learning structured sparsity in deep neural networks","volume":"abs 1608 3665","author":"wen","year":"2016","journal-title":"CoRR"},{"key":"ref41","first-page":"281","article-title":"Minimizing computation in convolutional neural networks","volume":"8681","author":"cong","year":"0","journal-title":"Artificial Neural Networks in Machine Learning"},{"key":"ref44","first-page":"2537","article-title":"Deep symmetry networks","author":"gens","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","article-title":"Reducing deep network complexity with Fourier transform methods","volume":"abs 1801 1451","author":"kiruluta","year":"2018","journal-title":"CoRR"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09389774.pdf?arnumber=9389774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T18:48:22Z","timestamp":1643222902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9389774\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3069906","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}