2018/06/30 by Xiao-Yu Dong, Xiaoyu Dong, Frank Pollmann +2 · 4 citations
Mathematics · Physics and Astronomy · #Advanced Thermodynamics and Statistical Mechanics #Algorithm #Artificial intelligence #Benchmark (surveying) #Computer science #Convolutional neural network #Machine learning #Mathematics #Monte Carlo method #Perspective (graphical) #Phase (matter) #Phase space #Phase transition #Physics #Quantum #Quantum many-body systems #Quantum mechanics #Quantum, superfluid, helium dynamics #Statistical physics #cond-mat.dis-nn #cond-mat.str-el
paper · pdf · doi:10.1103/physrevb.99.121104
published as Phys. Rev. B 99, 121104 (2019) · 6 pages, 5 figures
openalex publication_date 2019/03/07 · arxiv created 2019/03/17 · arxiv updated 2019/03/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Machine learning algorithms provide a new perspective on the study of physical phenomena. In this Rapid Communication, we explore the nature of quantum phase transitions using a multicolor convolutional neural network (CNN) in combination with quantum Monte Carlo simulations. We propose a method that compresses (d+1)-dimensional space-time configurations to a manageable size and then use them as the input for a CNN. We benchmark our approach on two models and show that both continuous and discontinuous quantum phase transitions can be well detected and characterized. Moreover, we show that intermediate phases, which were not trained, can also be identified using our approach.