Hybrid quantum-classical convolutional neural networks  

作　　者：Junhua Liu Kwan Hui Lim Kristin LWood Wei Huang Chu Guo He-Liang Huang 

机构地区：[1]Information Systems Technology and Design,Singapore University of Technology and Design,Singapore 487372,Singapore [2]Forth AI,Singapore 487372,Singapore [3]College of Engineering,Design and Computing,University of Colorado Denver,Colorado 80208,USA [4]Guangxi Key Laboratory of Optoelectronic Information Processing,Guilin University of Electronic Technology,Guilin 541004,China [5]Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education,Department of Physics and Synergetic Innovation Center for Quantum Effects and Applications,Hunan Normal University,Changsha 410081,China [6]Hefei National Laboratory for Physical Sciences at Microscale and Department of Modern Physics,University of Science and Technology of China,Hefei 230026,China [7]Shanghai Branch,CAS Centre for Excellence and Synergetic Innovation Centre in Quantum Information and Quantum Physics,University of Science and Technology of China,Hefei 201315,China [8]Henan Key Laboratory of Quantum Information and Cryptography,Zhengzhou 450000,China

出　　处：《Science China(Physics,Mechanics & Astronomy)》2021年第9期1-8,共8页中国科学：物理学、力学、天文学（英文版）

基　　金：support from the National Natural Science Foundation of China(Grant No.11805279).He-Liang Huang acknowledges support from the Youth Talent Lifting Project(Grant No.2020-JCJQ-QT-030),the National Natural Science Foundation of China(Grant No.11905294),the China Postdoctoral Science Foundation,and the Open Research Fund from State Key Laboratory of High Performance Computing of China(Grant No.201901-01).

摘　　要：Deep learning has been shown to be able to recognize data patterns better than humans in specific circumstances or contexts.In parallel,quantum computing has demonstrated to be able to output complex wave functions with a few number of gate operations,which could generate distributions that are hard for a classical computer to produce.Here we propose a hybrid quantum-classical convolutional neural network(QCCNN),inspired by convolutional neural networks(CNNs)but adapted to quantum computing to enhance the feature mapping process.QCCNN is friendly to currently noisy intermediate-scale quantum computers,in terms of both number of qubits as well as circuit’s depths,while retaining important features of classical CNN,such as nonlinearity and scalability.We also present a framework to automatically compute the gradients of hybrid quantum-classical loss functions which could be directly applied to other hybrid quantum-classical algorithms.We demonstrate the potential of this architecture by applying it to a Tetris dataset,and show that QCCNN can accomplish classification tasks with learning accuracy surpassing that of classical CNN with the same structure.

关 键 词：quantum computing quantum machine learning hybrid quantum-classical algorithm convolutional neural network 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP38[自动化与计算机技术—控制科学与工程]