Mohammad Hossein Nikzad, Mohammad Heidari-Rarani, Mohsen Mirkhalaf
{"title":"基于田口的优化神经网络架构新方法:应用于弹性短纤维复合材料","authors":"Mohammad Hossein Nikzad, Mohammad Heidari-Rarani, Mohsen Mirkhalaf","doi":"arxiv-2407.19802","DOIUrl":null,"url":null,"abstract":"This study presents an innovative application of the Taguchi design of\nexperiment method to optimize the structure of an Artificial Neural Network\n(ANN) model for the prediction of elastic properties of short fiber reinforced\ncomposites. The main goal is to minimize the required computational effort for\nhyperparameter optimization while enhancing the prediction accuracy. Utilizing\na robust design of experiment framework, the structure of an ANN model is\noptimized. This essentially is the identification of a combination of\nhyperparameters that yields an optimal predictive accuracy with the fewest\nalgorithmic runs, thereby achieving a significant reduction of the required\ncomputational effort. Our findings demonstrate that the Taguchi method not only\nstreamlines the hyperparameter tuning process but also could substantially\nimprove the algorithm's performance. These results underscore the potential of\nthe Taguchi method as a powerful tool for optimizing machine learning\nalgorithms, particularly in scenarios where computational resources are\nlimited. The implications of this study are far-reaching, offering insights for\nfuture research in the optimization of different algorithms for improved\naccuracies and computational efficiencies.","PeriodicalId":501309,"journal":{"name":"arXiv - CS - Computational Engineering, Finance, and Science","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A novel Taguchi-based approach for optimizing neural network architectures: application to elastic short fiber composites\",\"authors\":\"Mohammad Hossein Nikzad, Mohammad Heidari-Rarani, Mohsen Mirkhalaf\",\"doi\":\"arxiv-2407.19802\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study presents an innovative application of the Taguchi design of\\nexperiment method to optimize the structure of an Artificial Neural Network\\n(ANN) model for the prediction of elastic properties of short fiber reinforced\\ncomposites. The main goal is to minimize the required computational effort for\\nhyperparameter optimization while enhancing the prediction accuracy. Utilizing\\na robust design of experiment framework, the structure of an ANN model is\\noptimized. This essentially is the identification of a combination of\\nhyperparameters that yields an optimal predictive accuracy with the fewest\\nalgorithmic runs, thereby achieving a significant reduction of the required\\ncomputational effort. Our findings demonstrate that the Taguchi method not only\\nstreamlines the hyperparameter tuning process but also could substantially\\nimprove the algorithm's performance. These results underscore the potential of\\nthe Taguchi method as a powerful tool for optimizing machine learning\\nalgorithms, particularly in scenarios where computational resources are\\nlimited. The implications of this study are far-reaching, offering insights for\\nfuture research in the optimization of different algorithms for improved\\naccuracies and computational efficiencies.\",\"PeriodicalId\":501309,\"journal\":{\"name\":\"arXiv - CS - Computational Engineering, Finance, and Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computational Engineering, Finance, and Science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.19802\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computational Engineering, Finance, and Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.19802","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
本研究创新性地应用了田口试验设计法来优化人工神经网络(ANN)模型的结构,以预测短纤维增强复合材料的弹性性能。其主要目标是在提高预测精度的同时,最大限度地减少超参数优化所需的计算量。利用稳健的实验设计框架,对 ANN 模型的结构进行优化。这主要是指确定一个参数组合,以最少的算法运行次数获得最佳预测精度,从而显著减少所需的计算工作量。我们的研究结果表明,田口方法不仅简化了超参数调整过程,还能大幅提高算法性能。这些结果凸显了田口方法作为优化机器学习算法的强大工具的潜力,尤其是在计算资源有限的情况下。这项研究意义深远,为今后优化不同算法以提高准确性和计算效率的研究提供了启示。
A novel Taguchi-based approach for optimizing neural network architectures: application to elastic short fiber composites
This study presents an innovative application of the Taguchi design of
experiment method to optimize the structure of an Artificial Neural Network
(ANN) model for the prediction of elastic properties of short fiber reinforced
composites. The main goal is to minimize the required computational effort for
hyperparameter optimization while enhancing the prediction accuracy. Utilizing
a robust design of experiment framework, the structure of an ANN model is
optimized. This essentially is the identification of a combination of
hyperparameters that yields an optimal predictive accuracy with the fewest
algorithmic runs, thereby achieving a significant reduction of the required
computational effort. Our findings demonstrate that the Taguchi method not only
streamlines the hyperparameter tuning process but also could substantially
improve the algorithm's performance. These results underscore the potential of
the Taguchi method as a powerful tool for optimizing machine learning
algorithms, particularly in scenarios where computational resources are
limited. The implications of this study are far-reaching, offering insights for
future research in the optimization of different algorithms for improved
accuracies and computational efficiencies.