{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T08:34:43Z","timestamp":1792917283529,"version":"4.5.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Center for Brain Inspired Computing (C-BRIC), one of the six centers in JUMP","id":[{"id":"https:\/\/ror.org\/033tgbx59","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DoD Vannevar Bush Fellowship"},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.K. Ministry of Defence","award":["W911NF-16-3-0001"],"award-info":[{"award-number":["W911NF-16-3-0001"]}],"id":[{"id":"https:\/\/ror.org\/01bvxzn29","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2019.2961960","type":"journal-article","created":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T19:34:38Z","timestamp":1577216078000},"page":"1347-1360","source":"Crossref","is-referenced-by-count":50,"title":["A Low Effort Approach to Structured CNN Design Using PCA"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4702-9444","authenticated-orcid":false,"given":"Isha","family":"Garg","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4167-6782","authenticated-orcid":false,"given":"Priyadarshini","family":"Panda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0735-9695","authenticated-orcid":false,"given":"Kaushik","family":"Roy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Practical recommendations for gradient-based training of deep architectures","volume":"abs\/1206.5533","author":"Bengio","year":"2012","journal-title":"CoRR"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"ref3","article-title":"Deep residual learning for image recognition","volume":"abs\/1512.03385","author":"He","year":"2015","journal-title":"CoRR"},{"key":"ref4","article-title":"Predicting parameters in deep learning","volume":"abs\/1306.0543","author":"Denil","year":"2013","journal-title":"CoRR"},{"key":"ref5","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"arXiv:1510.00149","author":"Han","year":"2015"},{"key":"ref6","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref7","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref8","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","article-title":"Compression-aware training of deep networks","volume":"abs\/1711.02638","author":"Alvarez","year":"2017","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.5244\/C.28.88","article-title":"Speeding up convolutional neural networks with low rank expansions","volume-title":"arXiv:1405.3866","author":"Jaderberg","year":"2014"},{"key":"ref11","article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"arXiv:1611.06440","author":"Molchanov","year":"2016"},{"key":"ref12","article-title":"NISP: Pruning networks using neuron importance score propagation","volume":"abs\/1711.05908","author":"Yu","year":"2017","journal-title":"CoRR"},{"key":"ref13","first-page":"263","article-title":"Optimal brain surgeon: Extensions and performance comparisons","volume-title":"Proc. 6th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Hassibi"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2627369.2627613"},{"key":"ref15","article-title":"Pruning filters for efficient convNets","volume-title":"arXiv:1608.08710","author":"Li","year":"2016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12262"},{"key":"ref17","article-title":"ThiNet: A filter level pruning method for deep neural network compression","volume":"abs\/1707.06342","author":"Luo","year":"2017","journal-title":"CoRR"},{"key":"ref18","article-title":"SqueezeNet: AlexNet-level accuracy with 50X fewer parameters and <0.5 MB model size","volume":"abs\/1602.07360","author":"Iandola","year":"2016","journal-title":"CoRR"},{"key":"ref19","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","volume":"abs\/1704.04861","author":"Howard","year":"2017","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298809"},{"key":"ref21","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or \u22121","volume-title":"arXiv:1602.02830","author":"Courbariaux","year":"2016"},{"key":"ref22","article-title":"XNOR-Net: ImageNet classification using binary convolutional neural networks","volume":"abs\/1603.05279","author":"Rastegari","year":"2016","journal-title":"CoRR"},{"key":"ref23","article-title":"Training CNNs with low-rank filters for efficient image classification","volume-title":"arXiv:1511.06744","author":"Ioannou","year":"2015"},{"key":"ref24","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume":"abs\/1810.02340","author":"Lee","year":"2018","journal-title":"CoRR"},{"key":"ref25","article-title":"The lottery ticket hypothesis: Training pruned neural networks","volume":"abs\/1803.03635","author":"Frankle","year":"2018","journal-title":"CoRR"},{"key":"ref26","article-title":"Importance estimation for neural network pruning","volume":"abs\/1906.10771","author":"Molchanov","year":"2019","journal-title":"CoRR"},{"key":"ref27","first-page":"3177","article-title":"Net-Trim: Convex pruning of deep neural networks with performance guarantee","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Aghasi"},{"key":"ref28","first-page":"2181","article-title":"Runtime neural pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00890"},{"key":"ref30","article-title":"Learning sparse neural networks through \n$L_{0}$\n regularization","volume-title":"arXiv:1712.01312","author":"Louizos","year":"2017"},{"key":"ref31","article-title":"Nucleus neural network for super robust learning","volume":"abs\/1904.04036","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2695223"},{"key":"ref33","first-page":"875","article-title":"Discrimination-aware channel pruning for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhuang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00050"},{"key":"ref35","article-title":"Distilling the knowledge in a neural network","volume-title":"arXiv:1503.02531","author":"Hinton","year":"2015"},{"key":"ref36","article-title":"PCA-initialized deep neural networks applied to document image analysis","volume":"abs\/1702.00177","author":"Seuret","year":"2017","journal-title":"CoRR"},{"key":"ref37","article-title":"Explainable learning: Implicit generative modelling during training for adversarial robustness","volume":"abs\/1807.02188","author":"Panda","year":"2018","journal-title":"CoRR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1098\/rspl.1895.0041"},{"key":"ref39","volume-title":"Measure-Twice-Cut-Once","author":"Garg","year":"2018"},{"key":"ref40","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. 25th Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"1","author":"Krizhevsky"},{"key":"ref41","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems 32","author":"Paszke","year":"2019"},{"key":"ref42","volume-title":"Pytorch Classification","author":"Yang","year":"2018"},{"key":"ref43","volume-title":"Pytorch Toolbox","author":"Dawood","year":"2018"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/8948470\/8941144-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08941144.pdf?arnumber=8941144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T07:35:51Z","timestamp":1792913751000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8941144\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2961960","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}