Hybrid quantum ResNet for car classification and its hyperparameter optimization

IF 4.1 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Quantum Machine Intelligence Pub Date : 2023-09-29 DOI:10.1007/s42484-023-00123-2
Asel Sagingalieva, Mo Kordzanganeh, Andrii Kurkin, Artem Melnikov, Daniil Kuhmistrov, Michael Perelshtein, Alexey Melnikov, Andrea Skolik, David Von Dollen
{"title":"Hybrid quantum ResNet for car classification and its hyperparameter optimization","authors":"Asel Sagingalieva, Mo Kordzanganeh, Andrii Kurkin, Artem Melnikov, Daniil Kuhmistrov, Michael Perelshtein, Alexey Melnikov, Andrea Skolik, David Von Dollen","doi":"10.1007/s42484-023-00123-2","DOIUrl":null,"url":null,"abstract":"Abstract Image recognition is one of the primary applications of machine learning algorithms. Nevertheless, machine learning models used in modern image recognition systems consist of millions of parameters that usually require significant computational time to be adjusted. Moreover, adjustment of model hyperparameters leads to additional overhead. Because of this, new developments in machine learning models and hyperparameter optimization techniques are required. This paper presents a quantum-inspired hyperparameter optimization technique and a hybrid quantum-classical machine learning model for supervised learning. We benchmark our hyperparameter optimization method over standard black-box objective functions and observe performance improvements in the form of reduced expected run times and fitness in response to the growth in the size of the search space. We test our approaches in a car image classification task and demonstrate a full-scale implementation of the hybrid quantum ResNet model with the tensor train hyperparameter optimization. Our tests show a qualitative and quantitative advantage over the corresponding standard classical tabular grid search approach used with a deep neural network ResNet34. A classification accuracy of 0.97 was obtained by the hybrid model after 18 iterations, whereas the classical model achieved an accuracy of 0.92 after 75 iterations.","PeriodicalId":29924,"journal":{"name":"Quantum Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":4.1000,"publicationDate":"2023-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"18","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Quantum Machine Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s42484-023-00123-2","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 18

Abstract

Abstract Image recognition is one of the primary applications of machine learning algorithms. Nevertheless, machine learning models used in modern image recognition systems consist of millions of parameters that usually require significant computational time to be adjusted. Moreover, adjustment of model hyperparameters leads to additional overhead. Because of this, new developments in machine learning models and hyperparameter optimization techniques are required. This paper presents a quantum-inspired hyperparameter optimization technique and a hybrid quantum-classical machine learning model for supervised learning. We benchmark our hyperparameter optimization method over standard black-box objective functions and observe performance improvements in the form of reduced expected run times and fitness in response to the growth in the size of the search space. We test our approaches in a car image classification task and demonstrate a full-scale implementation of the hybrid quantum ResNet model with the tensor train hyperparameter optimization. Our tests show a qualitative and quantitative advantage over the corresponding standard classical tabular grid search approach used with a deep neural network ResNet34. A classification accuracy of 0.97 was obtained by the hybrid model after 18 iterations, whereas the classical model achieved an accuracy of 0.92 after 75 iterations.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
混合量子ResNet汽车分类及其超参数优化
摘要图像识别是机器学习算法的主要应用之一。然而,现代图像识别系统中使用的机器学习模型由数百万个参数组成,通常需要大量的计算时间来调整。此外,模型超参数的调整会导致额外的开销。因此,需要机器学习模型和超参数优化技术的新发展。本文提出了一种量子启发的超参数优化技术和一种用于监督学习的量子-经典混合机器学习模型。我们在标准黑盒目标函数上对我们的超参数优化方法进行了基准测试,并观察到随着搜索空间大小的增长,预期运行时间和适应度的减少,性能得到了改善。我们在一个汽车图像分类任务中测试了我们的方法,并展示了使用张量列超参数优化的混合量子ResNet模型的全尺寸实现。我们的测试表明,与使用深度神经网络ResNet34的相应标准经典表格网格搜索方法相比,该方法在定性和定量上都有优势。混合模型经过18次迭代得到0.97的分类精度,而经典模型经过75次迭代得到0.92的分类精度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
7.60
自引率
4.20%
发文量
29
期刊最新文献
Analyzing the effectiveness of quantum annealing with meta-learning SoK: quantum computing methods for machine learning optimization Evaluation of VQC-LSTM for disability forecasting in multiple sclerosis using sequential multisequence MRI Leveraging Quantum Kernel Support Vector Machine for breast cancer diagnosis from Digital Breast Tomosynthesis images Iteration-Free quantum approximate optimization algorithm using neural networks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1