A cautionary tale for machine learning generated configurations in presence of a conserved quantity
We investigate the performance of machine learning algorithms trained exclusively with configurations obtained from importance sampling Monte Carlo simulations of the two-dimensional Ising model with conserved magnetization. For supervised machine learning, we use convolutional neural networks and f...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7973807/ https://www.ncbi.nlm.nih.gov/pubmed/33737630 http://dx.doi.org/10.1038/s41598-021-85683-8 |