Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/148493
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTeo, Chee Seongen_US
dc.date.accessioned2021-04-28T02:37:35Z-
dc.date.available2021-04-28T02:37:35Z-
dc.date.issued2021-
dc.identifier.citationTeo, C. S. (2021). Adaptive learning rate for neural network. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/148493en_US
dc.identifier.urihttps://hdl.handle.net/10356/148493-
dc.description.abstractThe learning rate is one of the most important hyper-parameters to tune in a neural network and Deep Learning. The right choice of learning rate results in a better model and faster convergence during the learning process. Time is often wasted on selecting and tuning the learning rate. The purpose of this thesis is to present the Armijo learning rate (LR) to eliminate the need of manually selecting and tuning the learning rate. We first introduce related information to our work, including the foundation of the neural network. We discuss some current methods on selecting learning rate and propose the Armijo LR. We evaluate the Armijo LR with the current methods and evaluate their performance on some image classification data sets.en_US
dc.language.isoenen_US
dc.publisherNanyang Technological Universityen_US
dc.subjectScience::Mathematicsen_US
dc.titleAdaptive learning rate for neural networken_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorChua Chek Bengen_US
dc.contributor.schoolSchool of Physical and Mathematical Sciencesen_US
dc.description.degreeBachelor of Science in Mathematical Sciences and Economicsen_US
dc.contributor.supervisoremailCBChua@ntu.edu.sgen_US
item.grantfulltextrestricted-
item.fulltextWith Fulltext-
Appears in Collections:SPMS Student Reports (FYP/IA/PA/PI)
Files in This Item:
File Description SizeFormat 
Thesis_TeoCheeSeong_U1740371L.pdf
  Restricted Access
1.94 MBAdobe PDFView/Open

Page view(s)

169
Updated on Jun 30, 2022

Download(s)

17
Updated on Jun 30, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.