arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.00264quant-ph
收藏

用于增强图像分类的反射等变量子神经网络

Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification

Maxwell T. West, Martin Sevior, Muhammad Usman

AI总结:

本文提出反射等变量子神经网络,利用几何量子机器学习中的图像对称性,在真实图像分类任务上显著优于通用ansatz,缓解梯度消失和过拟合问题。

摘要:

机器学习是近期量子计算机最受期待的应用场景之一,但在其规模扩展方面仍存在重大的理论和实现挑战。特别是,越来越多的研究表明,通用的、与数据无关的量子机器学习(QML)架构可能存在严重的可训练性问题,典型变分参数的梯度会随量子比特数呈指数级消失。此外,QML模型的高表达性可能导致对训练数据过拟合,并造成泛化性能不佳。应对这两类困难的一个有前景的策略是构建明确尊重数据中固有对称性的模型,即所谓的几何量子机器学习(GQML)。在这项工作中,我们利用GQML技术处理图像分类任务,构建了相对于图像反射具有等变性的新型QML模型。我们发现,这些网络能够在复杂的真实世界图像数据集上持续且显著地优于通用ansatz,使通过量子计算机进行高分辨率图像分类更接近现实。我们的工作凸显了一条未来开发和实现强大QML模型的潜在路径,即直接利用数据的对称性。

英文摘要:

Machine learning is among the most widely anticipated use cases for near-term quantum computers, however there remain significant theoretical and implementation challenges impeding its scale up. In particular, there is an emerging body of work which suggests that generic, data agnostic quantum machine learning (QML) architectures may suffer from severe trainability issues, with the gradient of typical variational parameters vanishing exponentially in the number of qubits. Additionally, the high expressibility of QML models can lead to overfitting on training data and poor generalisation performance. A promising strategy to combat both of these difficulties is to construct models which explicitly respect the symmetries inherent in their data, so-called geometric quantum machine learning (GQML). In this work, we utilise the techniques of GQML for the task of image classification, building new QML models which are equivariant with respect to reflections of the images. We find that these networks are capable of consistently and significantly outperforming generic ansatze on complicated real-world image datasets, bringing high-resolution image classification via quantum computers closer to reality. Our work highlights a potential pathway for the future development and implementation of powerful QML models which directly exploit the symmetries of data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑