{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T15:22:02Z","timestamp":1725636122675},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,4,1]],"date-time":"2019-04-01T00:00:00Z","timestamp":1554076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1109\/wf-iot.2019.8767300","type":"proceedings-article","created":{"date-parts":[[2019,7,23]],"date-time":"2019-07-23T00:04:42Z","timestamp":1563840282000},"page":"346-351","source":"Crossref","is-referenced-by-count":3,"title":["Pulse-Net: Dynamic Compression of Convolutional Neural Networks"],"prefix":"10.1109","author":[{"given":"Browne","family":"Browne","sequence":"first","affiliation":[]},{"given":"Giering","family":"Giering","sequence":"additional","affiliation":[]},{"given":"Prestwich","family":"Prestwich","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","article-title":"Defending DNN Adversarial Attacks with Pruning and Logits Augmentation","author":"shaokai","year":"2018","journal-title":"ICLR Workshop"},{"key":"ref31","article-title":"Designing energy-efficient convolutional neural networks using energy-aware pruning","author":"yang","year":"2016","journal-title":"arXiv 1611 05128"},{"key":"ref30","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref11","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012","journal-title":"arXiv 1207 0580"},{"key":"ref12","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"NIPS*97 Workshop"},{"key":"ref13","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and¡ 1mb model size","author":"iandola","year":"2016","journal-title":"arXiv 1602 07360"},{"key":"ref14","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural network","author":"krizhevsky","year":"2012","journal-title":"In NIPS"},{"key":"ref15","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Master’s thesis"},{"key":"ref16","article-title":"Pruning Filters for Efficient ConvNets","author":"li","year":"2016","journal-title":"arXiv 1608 08710"},{"key":"ref17","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10449","article-title":"Face model compression by distilling knowledge from neurons","author":"luo","year":"2016","journal-title":"AAAI"},{"key":"ref19","article-title":"Variational dropout sparsifies deep neural networks","author":"molchanov","year":"2017","journal-title":"arXiv 1701 05369"},{"key":"ref28","article-title":"Highway networks","author":"szegedy","year":"2015","journal-title":"Proc ICML Deep Learn Workshop"},{"key":"ref4","first-page":"1269","article-title":"Predicting parameters in deep learning","author":"denil","year":"2014","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.525"},{"key":"ref3","article-title":"Binarized neural networks: Training neural networks with weights and activations constrained to +1 or -1","author":"courbariaux","year":"2016","journal-title":"arXiv 1602 02830 [cs]"},{"key":"ref6","first-page":"1379","article-title":"Dynamic network surgery for efficient dnns","author":"guo","year":"2016","journal-title":"In NIPS"},{"key":"ref29","article-title":"Adversarial Robustness of Pruned Neural Networks","author":"wang","year":"2018","journal-title":"ICLRE"},{"key":"ref5","article-title":"Deep residual learning for image recognition","author":"goodfellow","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref8","article-title":"Deep compression: Compressing DNNs with pruning, trained quantization and huffman coding","author":"han","year":"2015","journal-title":"arXiv 1510 00149 [cs]"},{"key":"ref7","article-title":"Learning both weights and connections for efficient neural networks","author":"han","year":"2015","journal-title":"In NIPS"},{"key":"ref2","first-page":"3105","article-title":"Binaryconnect: training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"In NIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref1","article-title":"Compressing neural networks with the hashing tr","author":"chen","year":"2015","journal-title":"In ICML"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2494536"},{"key":"ref22","article-title":"Fitnets: Hints for thin deep nets","author":"romero","year":"2015","journal-title":"ICLRE"},{"key":"ref21","article-title":"XNOR-Net: Ima-geNet Classification Using Binary Convolutional Neural Networks","author":"rastegari","year":"2016","journal-title":"In ECCV"},{"key":"ref24","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"ICLRE"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"ref25","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"srivastava","year":"2016","journal-title":"arXiv 1602 07261"}],"event":{"name":"2019 IEEE 5th World Forum on Internet of Things (WF-IoT'19)","start":{"date-parts":[[2019,4,15]]},"location":"Limerick, Ireland","end":{"date-parts":[[2019,4,18]]}},"container-title":["2019 IEEE 5th World Forum on Internet of Things (WF-IoT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8764305\/8767167\/08767300.pdf?arnumber=8767300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,24]],"date-time":"2022-09-24T10:42:50Z","timestamp":1664016170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8767300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/wf-iot.2019.8767300","relation":{},"subject":[],"published":{"date-parts":[[2019,4]]}}}