期刊
COMMUNICATIONS IN THEORETICAL PHYSICS
卷 74, 期 9, 页码 -出版社
IOP Publishing Ltd
DOI: 10.1088/1572-9494/ac7040
关键词
machine learning; quantum Boltzmann machine; quantum algorithm
资金
- National Natural Science Foundation of China [11725524]
- Hubei Provincal Natural Science Foundation of China [2019CFA003]
In this paper, quantum machine learning based on quantum algorithms is used to recognize handwritten number datasets by training the quantum Boltzmann machine (QBM) and comparing the results with classical models. It is found that, when the QBM is semi-restricted, better training results are achieved with fewer computing resources. This highlights the importance of designing targeted algorithms for faster computation and resource conservation.
Quantum machine learning based on quantum algorithms may achieve an exponential speedup over classical algorithms in dealing with some problems such as clustering. In this paper, we use the method of training the lower bound of the average log likelihood function on the quantum Boltzmann machine (QBM) to recognize the handwritten number datasets and compare the training results with classical models. We find that, when the QBM is semi-restricted, the training results get better with fewer computing resources. This shows that it is necessary to design a targeted algorithm to speed up computation and save resources.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据