The critical temperature of the 2D-Ising model through deep learning autoencoders
- PDF / 2,747,686 Bytes
- 15 Pages / 595.276 x 785.197 pts Page_size
- 117 Downloads / 171 Views
THE EUROPEAN PHYSICAL JOURNAL B
Regular Article
The critical temperature of the 2D-Ising model through deep learning autoencoders Constantia Alexandrou 1,2 , Andreas Athenodorou 3,a , Charalambos Chrysostomou 1 , and Srijit Paul 1,4 1
2 3 4
Computation-based Science and Technology Research Center, The Cyprus Institute, 20 Kavafi Str., 2121 Nicosia, Cyprus University of Cyprus, 1 Panepistimiou Avenue, 2109 Nicosia, Cyprus Dipartimento di Fisica, Universit` a di Pisa and INFN, Sezione di Pisa, Largo Pontecorvo 3, 56127 Pisa, Italy Faculty of Mathematics and Natural Sciences, University of Wuppertal, Gaussstr. 20, 42119 Wuppertal, Germany Received 21 October 2019 / Received in final form 20 September 2020 / Accepted 9 October 2020 Published online 7 December 2020 c The Author(s) 2020. This article is published with open access at Springerlink.com
Abstract. We investigate deep learning autoencoders for the unsupervised recognition of phase transitions in physical systems formulated on a lattice. We focus our investigation on the 2-dimensional ferromagnetic Ising model and then test the application of the autoencoder on the anti-ferromagnetic Ising model. We use spin configurations produced for the 2-dimensional ferromagnetic and anti-ferromagnetic Ising model in zero external magnetic field. For the ferromagnetic Ising model, we study numerically the relation between one latent variable extracted from the autoencoder to the critical temperature Tc . The proposed autoencoder reveals the two phases, one for which the spins are ordered and the other for which spins are disordered, reflecting the restoration of the Z2 symmetry as the temperature increases. We provide a finite volume analysis for a sequence of increasing lattice sizes. For the largest volume studied, the transition between the two phases occurs very close to the theoretically extracted critical temperature. We define as a quasiorder parameter the absolute average latent variable z˜, which enables us to predict the critical temperature. One can define a latent susceptibility and use it to quantify the value of the critical temperature Tc (L) at different lattice sizes and that these values suffer from only small finite scaling effects. We demonstrate that Tc (L) extrapolates to the known theoretical value as L → ∞ suggesting that the autoencoder can also be used to extract the critical temperature of the phase transition to an adequate precision. Subsequently, we test the application of the autoencoder on the anti-ferromagnetic Ising model, demonstrating that the proposed network can detect the phase transition successfully in a similar way.
1 Introduction Recent advances in the implementation of Artificial Intelligence (AI) for physical systems, especially, on those which can be formulated on a lattice, appear to be suitable for observing the corresponding underlying phase structure [1–17]. So far methods such as the Principal Component Analysis (PCA) [6,10,12,18,19], Supervised Machine Learning (ML) [2,15,20], Restricted Boltzmann Machines (RBMs) [21
Data Loading...
