@Article{cmc.2020.010865,
AUTHOR = {Xiaoyu Li, Qinsheng Zhu, Yiming Huang, Yong Hu, Qingyu Meng, Chenjing Su, Qing Yang, Shaoyi Wu, Xusheng Liu},
TITLE = {Research on the Freezing Phenomenon of Quantum Correlation  by Machine Learning},
JOURNAL = {Computers, Materials \& Continua},
VOLUME = {65},
YEAR = {2020},
NUMBER = {3},
PAGES = {2143--2151},
URL = {http://www.techscience.com/cmc/v65n3/40160},
ISSN = {1546-2226},
ABSTRACT = {Quantum correlation shows a fascinating nature of quantum mechanics and
plays an important role in some physics topics, especially in the field of quantum 
information. Quantum correlations of the composite system can be quantified by 
resorting to geometric or entropy methods, and all these quantification methods exhibit 
the peculiar freezing phenomenon. The challenge is to find the characteristics of the 
quantum states that generate the freezing phenomenon, rather than only study the 
conditions which generate this phenomenon under a certain quantum system. In essence, 
this is a classification problem. Machine learning has become an effective method for 
researchers to study classification and feature generation. In this work, we prove that the 
machine learning can solve the problem of X form quantum states, which is a problem of 
physical significance. Subsequently, we apply the density-based spatial clustering of 
applications with noise (DBSCAN) algorithm and the decision tree to divide quantum 
states into two different groups. Our goal is to classify the quantum correlations of 
quantum states into two classes: one is the quantum correlation with freezing 
phenomenon for both Rènyi discord (},
DOI = {10.32604/cmc.2020.010865}
}