PMID- 31325918
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20190722
IS  - 1089-7690 (Electronic)
IS  - 0021-9606 (Linking)
VI  - 151
IP  - 3
DP  - 2019 Jul 21
TI  - Generating the conformational properties of a polymer by the restricted Boltzmann 
      machine.
PG  - 031101
LID - 10.1063/1.5103210 [doi]
AB  - In polymer theory, computer-generated polymer configurations, by either Monte 
      Carlo simulations or molecular dynamics simulations, help us to establish the 
      fundamental understanding of the conformational properties of polymers. Here, we 
      introduce a different method, exploiting the properties of a machine-learning 
      algorithm, the restricted Boltzmann machine network, to generate independent 
      polymer configurations for self-avoiding walks (SAWs), for studying the 
      conformational properties of polymers. We show that with adequate training data 
      and network size, this method can capture the underlying polymer physics simply 
      from learning the statistics in the training data without explicit information on 
      the physical model itself. We critically examine how the trained Boltzmann 
      machine can generate independent configurations that are not in the original 
      training data set of SAWs.
FAU - Yu, Wancheng
AU  - Yu W
AUID- ORCID: 0000000205875629
AD  - School of Chemistry, Beihang University, Beijing 100191, China.
FAU - Liu, Yuan
AU  - Liu Y
AUID- ORCID: 0000000211567673
AD  - College of Chemistry and Molecular Engineering, Peking University, Beijing 
      100871, China.
FAU - Chen, Yuguo
AU  - Chen Y
AD  - School of Chemistry, Beihang University, Beijing 100191, China.
FAU - Jiang, Ying
AU  - Jiang Y
AUID- ORCID: 0000000260412272
AD  - School of Chemistry, Beihang University, Beijing 100191, China.
FAU - Chen, Jeff Z Y
AU  - Chen JZY
AUID- ORCID: 0000000279946231
AD  - Department of Physics and Astronomy, University of Waterloo, Waterloo, Ontario 
      N2L 3G1, Canada.
LA  - eng
PT  - Journal Article
PL  - United States
TA  - J Chem Phys
JT  - The Journal of chemical physics
JID - 0375360
EDAT- 2019/07/22 06:00
MHDA- 2019/07/22 06:01
CRDT- 2019/07/22 06:00
PHST- 2019/07/22 06:00 [entrez]
PHST- 2019/07/22 06:00 [pubmed]
PHST- 2019/07/22 06:01 [medline]
AID - 10.1063/1.5103210 [doi]
PST - ppublish
SO  - J Chem Phys. 2019 Jul 21;151(3):031101. doi: 10.1063/1.5103210.