Geodesic
Neural Network for Prediction of Curie Temperature of Two-Dimensional Ising Model
Dalʹnevostočnyj matematičeskij žurnal, Tome 21 (2021) no. 1, pp. 51-60 
A. O. Korol; V. Yu. Kapitan. Neural Network for Prediction of Curie Temperature of Two-Dimensional Ising Model. Dalʹnevostočnyj matematičeskij žurnal, Tome 21 (2021) no. 1, pp. 51-60. http://geodesic.mathdoc.fr/item/DVMG_2021_21_1_a4/
@article{DVMG_2021_21_1_a4,
     author = {A. O. Korol and V. Yu. Kapitan},
     title = {Neural {Network} for {Prediction} of {Curie} {Temperature} of {Two-Dimensional} {Ising} {Model}},
     journal = {Dalʹnevosto\v{c}nyj matemati\v{c}eskij \v{z}urnal},
     pages = {51--60},
     year = {2021},
     volume = {21},
     number = {1},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/DVMG_2021_21_1_a4/}
}
TY  - JOUR
AU  - A. O. Korol
AU  - V. Yu. Kapitan
TI  - Neural Network for Prediction of Curie Temperature of Two-Dimensional Ising Model
JO  - Dalʹnevostočnyj matematičeskij žurnal
PY  - 2021
SP  - 51
EP  - 60
VL  - 21
IS  - 1
UR  - http://geodesic.mathdoc.fr/item/DVMG_2021_21_1_a4/
LA  - ru
ID  - DVMG_2021_21_1_a4
ER  - 
%0 Journal Article
%A A. O. Korol
%A V. Yu. Kapitan
%T Neural Network for Prediction of Curie Temperature of Two-Dimensional Ising Model
%J Dalʹnevostočnyj matematičeskij žurnal
%D 2021
%P 51-60
%V 21
%N 1
%U http://geodesic.mathdoc.fr/item/DVMG_2021_21_1_a4/
%G ru
%F DVMG_2021_21_1_a4

Voir la notice de l'article provenant de la source Math-Net.Ru

The authors describe a method for determining the critical point of a second-order phase transitions using a convolutional neural network based on the Ising model on a square lattice. Data for training were obtained using Metropolis algorithm for different temperatures. The neural network was trained on the data corresponding to the low-temperature phase, that is a ferromagnetic one and high-temperature phase, that is a paramagnetic one, respectively. After training, the neural network analyzed input data from the entire temperature range: from $0.1$ to $5.0$ (in dimensionless units) and determined the Curie temperature $T_c$. The accuracy of the obtained results was estimated relative to the Onsager solution for a flat lattice of Ising spins.

[1] A.M. Turing, “Computing Machinery and Intelligence”, Mind, 59:236 (1950), 433–460 | DOI | MR

[2] A. G. Makarov i dr., “K chislennomu raschetu frustratsii v modeli Izinga”, Pisma v Zhurnal eksperimentalnoi i teoreticheskoi fiziki, 110:10 (2019), 700–705

[3] J. Carrasquilla and R.G. Melko, “Machine learning phases of matter”, Nature Physics, 13:5 (2017), 431–434 | DOI

[4] S. Kenta, et al., “Machine-Learning Studies on Spin Models”, Scientific Reports, 10:1 (2020) | Zbl

[5] K. V. Shapovalova i dr., “Metody kanonicheskogo i multikanonicheskogo semplirovaniya prostranstva sostoyanii vektornykh modelei”, Dalnevostochnyi matematicheskii zhurnal, 17:1 (2017), 124–130 | MR | Zbl

[6] V. Yu. Kapitan i dr., “Termodinamicheskie svoistva sistem spinov Geizenberga na kvadratnoi reshetke s vzaimodeistviem Dzyaloshinskogo–Moriya”, Dalnevostochnyi matematicheskii zhurnal, 20:1 (2020), 63–73 | MR | Zbl

[7] I. Goodfellow, Y. Bengio, A. Courville, Deep learning, MIT press, 2016 | MR | Zbl

[8] M. Abadi, et al., TensorFlow: Large-scale machine learning on heterogeneous systems, 2015 TensorFlow