Adaptive Weight Decay for Deep Neural Networks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Nakamura, Kensuke | - |
dc.contributor.author | Hong, Byung-Woo | - |
dc.date.available | 2020-04-23T09:20:39Z | - |
dc.date.issued | 2019-08 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/39048 | - |
dc.description.abstract | Regularization in the optimization of deep neural networks is often critical to avoid undesirable over-fitting leading to better generalization of model. One of the most popular regularization algorithms is to impose L-2 penalty on the model parameters resulting in the decay of parameters, called weight-decay, and the decay rate is generally constant to all the model parameters in the course of optimization. In contrast to the previous approach based on the constant rate of weight-decay, we propose to consider the residual that measures dissimilarity between the current state of model and observations in the determination of the weight-decay for each parameter in an adaptive way, called adaptive weight-decay (AdaDecay) where the gradient norms are normalized within each layer and the degree of regularization for each parameter is determined in proportional to the magnitude of its gradient using the sigmoid function. We empirically demonstrate the effectiveness of AdaDecay in comparison to the state-of-the-art optimization algorithms using popular benchmark datasets: MNIST, Fashion-MNIST, and CIFAR-10 with conventional neural network models ranging from shallow to deep. The quantitative evaluation of our proposed algorithm indicates that AdaDecay improves generalization leading to better accuracy across all the datasets and models. | - |
dc.format.extent | 9 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Adaptive Weight Decay for Deep Neural Networks | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ACCESS.2019.2937139 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.7, pp 118857 - 118865 | - |
dc.description.isOpenAccess | Y | - |
dc.identifier.wosid | 000484355600004 | - |
dc.identifier.scopusid | 2-s2.0-85095375118 | - |
dc.citation.endPage | 118865 | - |
dc.citation.startPage | 118857 | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 7 | - |
dc.type.docType | Article | - |
dc.publisher.location | 미국 | - |
dc.subject.keywordAuthor | Adaptive regularization | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | neural networks | - |
dc.subject.keywordAuthor | stochastic gradient descent | - |
dc.subject.keywordAuthor | weight-decay | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.