arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.15073quant-phcs.AI
收藏

用于神经架构搜索的分层量子电路表示

Hierarchical quantum circuit representations for neural architecture search

Stellenbosch University(斯坦陵布什大学);University of KwaZulu-Natal(夸祖鲁-纳塔尔大学);National Institute for Theoretical and Computational Sciences (NITheCS)(国家理论与计算科学研究所);Yonsei University(延世大学);Data Cybernetics(数据控制论机构);School of Data Science and Computational Thinking, Stellenbosch University(斯坦陵布什大学数据科学与计算思维学院)

Matt Lourens, Ilya Sinayskiy, Daniel K. Park, Carsten Blank, Francesco Petruccione

AI总结:

本文提出面向QCNN的NAS表示框架,可定义搜索空间、生成反向二叉树式架构,并通过GTZAN评估和遗传算法QPR搜索验证其提升性能、规避贫瘠高原的作用。

摘要:

使用分层量子电路的机器学习通常被称为量子卷积神经网络(QCNN),对近期量子计算而言是一个很有前景的方向。QCNN是一种受卷积神经网络(CNN)架构启发的电路模型。CNN之所以成功,是因为它们不需要人工设计特征,并能够从原始数据中学习高级特征。神经架构搜索(NAS)在这一成功基础上进一步学习网络架构,并取得了最先进的性能。然而,由于缺乏定义良好的搜索空间,将NAS应用于QCNN会带来独特的挑战。在本研究中,我们提出了一种利用NAS技术表示QCNN架构的新颖框架,该框架支持搜索空间设计和架构搜索。利用这一框架,我们生成了一类流行的QCNN,即那些类似反向二叉树的QCNN。随后,我们在音乐流派分类数据集GTZAN上评估这一系列模型,以证明电路架构的重要性。此外,我们采用遗传算法执行量子相位识别(QPR),作为使用我们的表示进行架构搜索的示例。本研究提供了一种在不增加复杂性的情况下提升模型性能的方法,并可在代价景观中跳转以避免贫瘠高原。最后,我们将该框架实现为一个开源Python包,以支持动态QCNN创建,并促进用于NAS的QCNN搜索空间设计。

英文摘要:

Machine learning with hierarchical quantum circuits, usually referred to as Quantum Convolutional Neural Networks (QCNNs), is a promising prospect for near-term quantum computing. The QCNN is a circuit model inspired by the architecture of Convolutional Neural Networks (CNNs). CNNs are successful because they do not need manual feature design and can learn high-level features from raw data. Neural Architecture Search (NAS) builds on this success by learning network architecture and achieves state-of-the-art performance. However, applying NAS to QCNNs presents unique challenges due to the lack of a well-defined search space. In this work, we propose a novel framework for representing QCNN architectures using techniques from NAS, which enables search space design and architecture search. Using this framework, we generate a family of popular QCNNs, those resembling reverse binary trees. We then evaluate this family of models on a music genre classification dataset, GTZAN, to justify the importance of circuit architecture. Furthermore, we employ a genetic algorithm to perform Quantum Phase Recognition (QPR) as an example of architecture search with our representation. This work provides a way to improve model performance without increasing complexity and to jump around the cost landscape to avoid barren plateaus. Finally, we implement the framework as an open-source Python package to enable dynamic QCNN creation and facilitate QCNN search space design for NAS.

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。

↑