arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.03066quant-phcs.CVcs.LG
收藏

量子神经网络在生成学习中的研究进展

Recent Advances for Quantum Neural Networks in Generative Learning

Defense Innovation Institute(国防创新研究院);Tianjin Artificial Intelligence Innovation Center(天津人工智能创新中心);Imperial College London(帝国理工学院);JD Explore Academy(京东探索研究院);National University of Defense Technology(国防科技大学);The University of Sydney(悉尼大学);Hon Hai (Foxconn) Research Institute(鸿海(富士康)研究院)
Jinkai Tian, Xiaoyu Sun, Yuxuan Du, Shanshan Zhao, Qing Liu, Kaining Zhang, Wei Yi, Wanrong Huang, Chaoyue Wang, Xingyao Wu, Min-Hsiu Hsieh, Tongliang Liu, Wenj… 展开作者

Jinkai Tian, Xiaoyu Sun, Yuxuan Du, Shanshan Zhao, Qing Liu, Kaining Zhang, Wei Yi, Wanrong Huang, Chaoyue Wang, Xingyao Wu, Min-Hsiu Hsieh, Tongliang Liu, Wenjing Yang, Dacheng Tao

摘要:

量子计算机是下一代设备,有望执行超越经典计算机的计算。实现这一目标的主要方法是通过量子机器学习,特别是量子生成学习。由于量子力学固有的概率性质,可以合理地假设量子生成学习模型(QGLM)可能超过其经典模型。因此,QGLM正受到量子物理和计算机科学界越来越多的关注,其中提出了可以在近期量子机器上有效实现的具有潜在计算优势的各种QGLM。本文从机器学习的角度对QGLM的研究进展进行了综述。特别是,我们解释这些QGLM,涵盖量子线路出生的机器,量子生成对抗网络,量子玻尔兹曼机和量子自动编码器,作为经典生成学习模型的量子扩展。在此背景下,我们探讨了它们的内在联系和根本区别。我们进一步总结了QGLM在传统机器学习任务和量子物理中的潜在应用。最后,我们讨论了QGLM面临的挑战和进一步的研究方向。

英文摘要:

Quantum computers are next-generation devices that hold promise to perform calculations beyond the reach of classical computers. A leading method towards achieving this goal is through quantum machine learning, especially quantum generative learning. Due to the intrinsic probabilistic nature of quantum mechanics, it is reasonable to postulate that quantum generative learning models (QGLMs) may surpass their classical counterparts. As such, QGLMs are receiving growing attention from the quantum physics and computer science communities, where various QGLMs that can be efficiently implemented on near-term quantum machines with potential computational advantages are proposed. In this paper, we review the current progress of QGLMs from the perspective of machine learning. Particularly, we interpret these QGLMs, covering quantum circuit born machines, quantum generative adversarial networks, quantum Boltzmann machines, and quantum autoencoders, as the quantum extension of classical generative learning models. In this context, we explore their intrinsic relation and their fundamental differences. We further summarize the potential applications of QGLMs in both conventional machine learning tasks and quantum physics. Last, we discuss the challenges and further research directions for QGLMs.

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。

↑