Exploring neural network training strategies to determine phase transitions in frustrated magnetic models
The transfer learning of a neural network is one of its most outstanding aspects and has given supervised learning with neural networks a prominent place in data science. Here we explore this feature in the context of strongly interacting many-body systems. Through case studies, we test the potentia...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | Articulo |
Lenguaje: | Inglés |
Publicado: |
2021
|
Materias: | |
Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/131979 |
Aporte de: |
id |
I19-R120-10915-131979 |
---|---|
record_format |
dspace |
institution |
Universidad Nacional de La Plata |
institution_str |
I-19 |
repository_str |
R-120 |
collection |
SEDICI (UNLP) |
language |
Inglés |
topic |
Ingeniería Física Frustrated magnetism Machine learning Ising model Honeycomb lattice Square lattice Neural networks |
spellingShingle |
Ingeniería Física Frustrated magnetism Machine learning Ising model Honeycomb lattice Square lattice Neural networks Corte, Inés Raquel Acevedo, Santiago Daniel Arlego, Marcelo José Fabián Lamas, Carlos Alberto Exploring neural network training strategies to determine phase transitions in frustrated magnetic models |
topic_facet |
Ingeniería Física Frustrated magnetism Machine learning Ising model Honeycomb lattice Square lattice Neural networks |
description |
The transfer learning of a neural network is one of its most outstanding aspects and has given supervised learning with neural networks a prominent place in data science. Here we explore this feature in the context of strongly interacting many-body systems. Through case studies, we test the potential of this deep learning technique to detect phases and their transitions in frustrated spin systems, using fully-connected and convolutional neural networks. In addition, we explore a recently-introduced technique, which is at the middle point of supervised and unsupervised learning. It consists in evaluating the performance of a neural network that has been deliberately “confused” during its training. To properly demonstrate the capability of the “confusion” and transfer learning techniques, we apply them to a paradigmatic model of frustrated magnetism in two dimensions, to determine its phase diagram and compare it with high-performance Monte Carlo simulations. |
format |
Articulo Articulo |
author |
Corte, Inés Raquel Acevedo, Santiago Daniel Arlego, Marcelo José Fabián Lamas, Carlos Alberto |
author_facet |
Corte, Inés Raquel Acevedo, Santiago Daniel Arlego, Marcelo José Fabián Lamas, Carlos Alberto |
author_sort |
Corte, Inés Raquel |
title |
Exploring neural network training strategies to determine phase transitions in frustrated magnetic models |
title_short |
Exploring neural network training strategies to determine phase transitions in frustrated magnetic models |
title_full |
Exploring neural network training strategies to determine phase transitions in frustrated magnetic models |
title_fullStr |
Exploring neural network training strategies to determine phase transitions in frustrated magnetic models |
title_full_unstemmed |
Exploring neural network training strategies to determine phase transitions in frustrated magnetic models |
title_sort |
exploring neural network training strategies to determine phase transitions in frustrated magnetic models |
publishDate |
2021 |
url |
http://sedici.unlp.edu.ar/handle/10915/131979 |
work_keys_str_mv |
AT corteinesraquel exploringneuralnetworktrainingstrategiestodeterminephasetransitionsinfrustratedmagneticmodels AT acevedosantiagodaniel exploringneuralnetworktrainingstrategiestodeterminephasetransitionsinfrustratedmagneticmodels AT arlegomarcelojosefabian exploringneuralnetworktrainingstrategiestodeterminephasetransitionsinfrustratedmagneticmodels AT lamascarlosalberto exploringneuralnetworktrainingstrategiestodeterminephasetransitionsinfrustratedmagneticmodels |
bdutipo_str |
Repositorios |
_version_ |
1764820453750210563 |