文献类型：期刊文献

英文题名：Deep Ising Born Machine

作者：Cao, Zhu[1]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

年份：2023

卷号：6

期号：7

外文期刊名：ADVANCED QUANTUM TECHNOLOGIES

收录：;EI(收录号：20230128757);WOS:【SCI-EXPANDED(收录号:WOS:000976056600001)】；

基金：This work was supported by the National Natural Science Foundation of China (Basic Science Center Program: 61988101), the National Natural Science Foundation of China (12105105), the Natural Science Foundation of Shanghai (21ZR1415800), the Shanghai Sailing Program (21YF1409800), and the startup fund from East China University of Science and Technology (JKH01221665 and YH0142206).

语种：英文

外文关键词：efficiency; expressivity; quantum machine learning; quantum neural network; universality

摘要：A quantum neural network (QNN) is a method to find patterns in quantum data and has a wide range of applications including quantum chemistry, quantum computation, quantum metrology, and quantum simulation. Efficiency and universality are two desirable properties of a QNN but are unfortunately contradictory. In this work, a deep Ising Born machine (DIBoM) is examined, and shown that it has a good balance between efficiency and universality. More precisely, the DIBoM has a flexible number of parameters to be efficient, and achieves provable universality with sufficient parameters. The architecture of the DIBoM is based on generalized controlled-Z gates, conditional gates, and some other ingredients. To compare the universality of the DIBoM with other QNNs, a fidelity-based expressivity measure is proposed, which may be of independent interest. Extensive empirical evaluations corroborate that the DIBoM is both efficient and expressive.