Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning

We apply unsupervised learning techniques to classify the different phases of the J₁-J₂ antiferromagnetic Ising model on the honeycomb lattice. We construct the phase diagram of the system using convolutional autoencoders. These neural networks can detect phase transitions in the system via "an...

Descripción completa

Detalles Bibliográficos
Autores principales: Acevedo, Santiago Daniel, Arlego, Marcelo José Fabián, Lamas, Carlos Alberto
Formato: Articulo Preprint
Lenguaje:Inglés
Publicado: 2021
Materias:
Física
Autoencoder
Physics
Statistical physics
Phase transition
Degeneracy (mathematics)
Lattice (group)
Artificial neural network
Ising model
Unsupervised learning
Phase diagram
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/125201
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-125201
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Física
Autoencoder
Physics
Statistical physics
Phase transition
Degeneracy (mathematics)
Lattice (group)
Artificial neural network
Ising model
Unsupervised learning
Phase diagram
spellingShingle Física
Autoencoder
Physics
Statistical physics
Phase transition
Degeneracy (mathematics)
Lattice (group)
Artificial neural network
Ising model
Unsupervised learning
Phase diagram
Acevedo, Santiago Daniel
Arlego, Marcelo José Fabián
Lamas, Carlos Alberto
Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
topic_facet Física
Autoencoder
Physics
Statistical physics
Phase transition
Degeneracy (mathematics)
Lattice (group)
Artificial neural network
Ising model
Unsupervised learning
Phase diagram
description We apply unsupervised learning techniques to classify the different phases of the J₁-J₂ antiferromagnetic Ising model on the honeycomb lattice. We construct the phase diagram of the system using convolutional autoencoders. These neural networks can detect phase transitions in the system via "anomaly detection'' without the need for any label or a priori knowledge of the phases. We present different ways of training these autoencoders, and we evaluate them to discriminate between distinct magnetic phases. In this process, we highlight the case of high-temperature or even random training data. Finally, we analyze the capability of the autoencoder to detect the ground state degeneracy through the reconstruction error.
format Articulo
Preprint
author Acevedo, Santiago Daniel
Arlego, Marcelo José Fabián
Lamas, Carlos Alberto
author_facet Acevedo, Santiago Daniel
Arlego, Marcelo José Fabián
Lamas, Carlos Alberto
author_sort Acevedo, Santiago Daniel
title Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
title_short Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
title_full Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
title_fullStr Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
title_full_unstemmed Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
title_sort phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
publishDate 2021
url http://sedici.unlp.edu.ar/handle/10915/125201
work_keys_str_mv AT acevedosantiagodaniel phasediagramstudyofatwodimensionalfrustratedantiferromagnetviaunsupervisedmachinelearning
AT arlegomarcelojosefabian phasediagramstudyofatwodimensionalfrustratedantiferromagnetviaunsupervisedmachinelearning
AT lamascarlosalberto phasediagramstudyofatwodimensionalfrustratedantiferromagnetviaunsupervisedmachinelearning
bdutipo_str Repositorios
_version_ 1764820451372040193

Ejemplares similares