On the neural network flow of spin configurations

We study the so-called neural network flow of spin configurations in the 2-d Ising ferromagnet. This flow is generated by successive reconstructions of spin configurations, obtained by an artificial neural network like a restricted Boltzmann machine or an autoencoder. It was reported recently that t...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computational materials science Ročník 213; s. 111634
Hlavní autori: Acevedo, Santiago, Lamas, Carlos A., Costa Duran, Alejo, Sturla, Mauricio B., Grigera, Tomás S.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.10.2022
Predmet:
ISSN:0927-0256, 1879-0801
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:We study the so-called neural network flow of spin configurations in the 2-d Ising ferromagnet. This flow is generated by successive reconstructions of spin configurations, obtained by an artificial neural network like a restricted Boltzmann machine or an autoencoder. It was reported recently that this flow may have a fixed point at the critical temperature of the system, and even allow the computation of critical exponents. Here we focus on the flow produced by a fully-connected autoencoder, and we refute the claim that this flow converges to the critical point of the system by directly measuring physical observables, and showing that the flow strongly depends on the network hyperparameters. We explore the network metric, the reconstruction error, and we relate it to the so called intrinsic dimension of data, to shed light on the origin and properties of the flow. [Display omitted] •Proof that the neural network flow does not end in the critical point of the system.•Relationship between compression in Autoencoders and the intrinsic dimension of data.•Study of the flow dependence with hyperparameters.
ISSN:0927-0256
1879-0801
DOI:10.1016/j.commatsci.2022.111634