Skip navigation
Run Run Shaw Library City University of Hong KongRun Run Shaw Library

Please use this identifier to cite or link to this item: http://dspace.cityu.edu.hk/handle/2031/9050
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChau, Kwan Yinen_US
dc.date.accessioned2019-01-17T04:30:17Z
dc.date.accessioned2019-02-12T07:27:53Z-
dc.date.available2019-01-17T04:30:17Z
dc.date.available2019-02-12T07:27:53Z-
dc.date.issued2017en_US
dc.identifier.other2017eecky887en_US
dc.identifier.urihttp://144.214.8.231/handle/2031/9050-
dc.description.abstractConvolutional Neural Network is a common way to address image recognition problems in recent years. Among these years, some new ideas which related to CNN is found, such as dropout and batch normalization. In this project, CNN models are built based on two famous model architecture. Initialization of parameters are chosen carefully. Experiments were done on different architectures and parameters. Results are found which match the mathematical and statistical theories supported behind.en_US
dc.titleTraffic Sign Recognition by Deep Learningen_US
dc.contributor.departmentDepartment of Electronic Engineeringen_US
dc.description.supervisorSupervisor: Mr. Ting, Van C W; Assessor: Mr. Ng, Kai Taten_US
Appears in Collections:Electrical Engineering - Undergraduate Final Year Projects 

Files in This Item:
File SizeFormat 
fulltext.html148 BHTMLView/Open
Show simple item record


Items in Digital CityU Collections are protected by copyright, with all rights reserved, unless otherwise indicated.

Send feedback to Library Systems
Privacy Policy | Copyright | Disclaimer