Improve the Hunger Games search algorithm to optimize the GoogleNet model.

The setting of parameter values will directly affect the performance of the neural network, and the manual parameter tuning speed is slow, and it is difficult to find the optimal combination of parameters. Based on this, this paper applies the improved Hunger Games search algorithm to find the optim...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanqiu Li, Shizheng Qu, Huan Liu
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2024-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0305653
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850169596794896384
author Yanqiu Li
Shizheng Qu
Huan Liu
author_facet Yanqiu Li
Shizheng Qu
Huan Liu
author_sort Yanqiu Li
collection DOAJ
description The setting of parameter values will directly affect the performance of the neural network, and the manual parameter tuning speed is slow, and it is difficult to find the optimal combination of parameters. Based on this, this paper applies the improved Hunger Games search algorithm to find the optimal value of neural network parameters adaptively, and proposes an ATHGS-GoogleNet model. Firstly, adaptive weights and chaos mapping were integrated into the hunger search algorithm to construct a new algorithm, ATHGS. Secondly, the improved ATHGS algorithm was used to optimize the parameters of GoogleNet to construct a new model, ATHGS-GoogleNet. Finally, in order to verify the effectiveness of the proposed algorithm ATHGS and the model ATHGS-GoogleNet, a comparative experiment was set up. Experimental results show that the proposed algorithm ATHGS shows the best optimization performance in the three engineering experimental designs, and the accuracy of the proposed model ATHGS-GoogleNet reaches 98.1%, the sensitivity reaches 100%, and the precision reaches 99.5%.
format Article
id doaj-art-3944495ee5c64fefacea1ca99fae6b9f
institution OA Journals
issn 1932-6203
language English
publishDate 2024-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-3944495ee5c64fefacea1ca99fae6b9f2025-08-20T02:20:41ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-01198e030565310.1371/journal.pone.0305653Improve the Hunger Games search algorithm to optimize the GoogleNet model.Yanqiu LiShizheng QuHuan LiuThe setting of parameter values will directly affect the performance of the neural network, and the manual parameter tuning speed is slow, and it is difficult to find the optimal combination of parameters. Based on this, this paper applies the improved Hunger Games search algorithm to find the optimal value of neural network parameters adaptively, and proposes an ATHGS-GoogleNet model. Firstly, adaptive weights and chaos mapping were integrated into the hunger search algorithm to construct a new algorithm, ATHGS. Secondly, the improved ATHGS algorithm was used to optimize the parameters of GoogleNet to construct a new model, ATHGS-GoogleNet. Finally, in order to verify the effectiveness of the proposed algorithm ATHGS and the model ATHGS-GoogleNet, a comparative experiment was set up. Experimental results show that the proposed algorithm ATHGS shows the best optimization performance in the three engineering experimental designs, and the accuracy of the proposed model ATHGS-GoogleNet reaches 98.1%, the sensitivity reaches 100%, and the precision reaches 99.5%.https://doi.org/10.1371/journal.pone.0305653
spellingShingle Yanqiu Li
Shizheng Qu
Huan Liu
Improve the Hunger Games search algorithm to optimize the GoogleNet model.
PLoS ONE
title Improve the Hunger Games search algorithm to optimize the GoogleNet model.
title_full Improve the Hunger Games search algorithm to optimize the GoogleNet model.
title_fullStr Improve the Hunger Games search algorithm to optimize the GoogleNet model.
title_full_unstemmed Improve the Hunger Games search algorithm to optimize the GoogleNet model.
title_short Improve the Hunger Games search algorithm to optimize the GoogleNet model.
title_sort improve the hunger games search algorithm to optimize the googlenet model
url https://doi.org/10.1371/journal.pone.0305653
work_keys_str_mv AT yanqiuli improvethehungergamessearchalgorithmtooptimizethegooglenetmodel
AT shizhengqu improvethehungergamessearchalgorithmtooptimizethegooglenetmodel
AT huanliu improvethehungergamessearchalgorithmtooptimizethegooglenetmodel