Variable three-term conjugate gradient method for training artificial neural networks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Hansu | - |
dc.contributor.author | Wang, Chuxuan | - |
dc.contributor.author | Byun, Hyoseok | - |
dc.contributor.author | Hu, Weifei | - |
dc.contributor.author | Kim, Sanghyuk | - |
dc.contributor.author | Jiao, Qing | - |
dc.contributor.author | Lee, Tae Hee | - |
dc.date.accessioned | 2023-05-03T11:09:11Z | - |
dc.date.available | 2023-05-03T11:09:11Z | - |
dc.date.created | 2023-01-05 | - |
dc.date.issued | 2023-02 | - |
dc.identifier.issn | 0893-6080 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/185158 | - |
dc.description.abstract | Artificial neural networks (ANNs) have been widely adopted as general computational tools both in computer science as well as many other engineering fields. Stochastic gradient descent (SGD) and adaptive methods such as Adam are popular as robust optimization algorithms used to train the ANNs. However, the effectiveness of these algorithms is limited because they calculate a search direction based on a first-order gradient. Although higher-order gradient methods such as Newton's method have been proposed, they require the Hessian matrix to be semi-definite, and its inversion incurs a high computational cost. Therefore, in this paper, we propose a variable three-term conjugate gradient (VTTCG) method that approximates the Hessian matrix to enhance search direction and uses a variable step size to achieve improved convergence stability. To evaluate the performance of the VTTCG method, we train different ANNs on benchmark image classification and generation datasets. We also conduct a similar experiment in which a grasp generation and selection convolutional neural network (GGS-CNN) is trained to perform intelligent robotic grasping. After considering a simulated environment, we also test the GGS-CNN with a physical grasping robot. The experimental results show that the performance of the VTTCG method is superior to that of four conventional methods, including SGD, Adam, AMSGrad, and AdaBelief. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.title | Variable three-term conjugate gradient method for training artificial neural networks | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, Tae Hee | - |
dc.identifier.doi | 10.1016/j.neunet.2022.12.001 | - |
dc.identifier.scopusid | 2-s2.0-85144522968 | - |
dc.identifier.wosid | 000910215000001 | - |
dc.identifier.bibliographicCitation | NEURAL NETWORKS, v.159, pp.125 - 136 | - |
dc.relation.isPartOf | NEURAL NETWORKS | - |
dc.citation.title | NEURAL NETWORKS | - |
dc.citation.volume | 159 | - |
dc.citation.startPage | 125 | - |
dc.citation.endPage | 136 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Neurosciences & Neurology | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Neurosciences | - |
dc.subject.keywordPlus | Benchmarking | - |
dc.subject.keywordPlus | Classification (of information) | - |
dc.subject.keywordPlus | Conjugate gradient method | - |
dc.subject.keywordPlus | Intelligent robots | - |
dc.subject.keywordPlus | Inverse problems | - |
dc.subject.keywordPlus | Neural networks | - |
dc.subject.keywordPlus | Newton-Raphson method | - |
dc.subject.keywordPlus | Optimization | - |
dc.subject.keywordPlus | Stochastic systems | - |
dc.subject.keywordPlus | Conjugate-gradient method | - |
dc.subject.keywordPlus | Image generations | - |
dc.subject.keywordPlus | Images classification | - |
dc.subject.keywordPlus | Intelligent robotic grasping | - |
dc.subject.keywordPlus | Intelligent robotics | - |
dc.subject.keywordPlus | Robotic grasping | - |
dc.subject.keywordPlus | Search direction | - |
dc.subject.keywordPlus | Three-term | - |
dc.subject.keywordPlus | Three-term conjugate gradient | - |
dc.subject.keywordPlus | Variable step size | - |
dc.subject.keywordAuthor | Three-term conjugate gradient | - |
dc.subject.keywordAuthor | Variable step size | - |
dc.subject.keywordAuthor | Artificial neural networks | - |
dc.subject.keywordAuthor | Image classification and generation | - |
dc.subject.keywordAuthor | Intelligent robotic grasping | - |
dc.identifier.url | https://www.sciencedirect.com/science/article/pii/S0893608022004932?via%3Dihub | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
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.