{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T06:43:57Z","timestamp":1740120237428,"version":"3.37.3"},"reference-count":14,"publisher":"World Scientific Pub Co Pte Ltd","issue":"10","funder":[{"name":"The National Key Research and Development Program of China","award":["2017YFB1400803"],"award-info":[{"award-number":["2017YFB1400803"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2020,9]]},"abstract":"<jats:p> Currently, Deep Learning and Convolutional Neural Network (CNN) have been widely used in many fields and have generated very high value in these fields, especially in the field of image recognition. But there are some deficiencies in certain issues of image recognition. For example, CNN\u2019s recognizing performance is not good at different angles of objects and overlapping objects. Also, CNN is sometimes very sensitive to slight perturbations, modifying one pixel of a recognized image may cause recognition errors. For these problems, the capsule network (CapsNet) proposed by Geoffrey Hinton can solve the problems of traditional convolutional networks. Shortly after CapsNet was proposed, the model structure was relatively simple, and many aspects could be explored for improvement. This paper will optimize CapsNet from two aspects: \u201coptimization of routing mechanism\u201d and \u201cincrease Dropout operation.\u201d And carry out experiments and results analysis on these optimizations. <\/jats:p>","DOI":"10.1142\/s0218001420520060","type":"journal-article","created":{"date-parts":[[2019,10,30]],"date-time":"2019-10-30T03:40:49Z","timestamp":1572406849000},"page":"2052006","source":"Crossref","is-referenced-by-count":0,"title":["Efficiency Optimization of Capsule Network Model Based on Vector Element"],"prefix":"10.1142","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9951-6837","authenticated-orcid":false,"given":"Lijuan","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Information Engineering, Capital Normal University, Beijing, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Capital Normal University, Beijing, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Capital Normal University, Beijing, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shudong","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Capital Normal University, Beijing, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Capital Normal University, Beijing, P.\u00a0R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2020,1,8]]},"reference":[{"key":"S0218001420520060BIB001","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"S0218001420520060BIB003","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"S0218001420520060BIB004","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.04.006"},{"key":"S0218001420520060BIB005","doi-asserted-by":"publisher","DOI":"10.1109\/72.554195"},{"issue":"6","key":"S0218001420520060BIB006","first-page":"1","author":"Li Y.","year":"2018","journal-title":"Cluster Comput."},{"issue":"5","key":"S0218001420520060BIB009","first-page":"2829","volume":"263","author":"Russell S. J.","year":"2010","journal-title":"Appl. Mech. Mater."},{"key":"S0218001420520060BIB010","first-page":"3856","author":"Sabour S.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Deep Learning in Neural Networks","year":"2015","author":"Schmidhuber J.","key":"S0218001420520060BIB011"},{"issue":"1","key":"S0218001420520060BIB013","first-page":"1929","volume":"15","author":"Srivastava N.","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"S0218001420520060BIB014","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1996.557235"},{"key":"S0218001420520060BIB015","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"S0218001420520060BIB016","doi-asserted-by":"publisher","DOI":"10.1111\/os.12439"},{"volume-title":"Bioinformatics","year":"2018","author":"Wang D.","key":"S0218001420520060BIB017"},{"key":"S0218001420520060BIB020","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2018.05.032"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001420520060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,14]],"date-time":"2020-09-14T10:18:14Z","timestamp":1600078694000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0218001420520060"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,8]]},"references-count":14,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["10.1142\/S0218001420520060"],"URL":"https:\/\/doi.org\/10.1142\/s0218001420520060","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2020,1,8]]}}}