A comment on the training of unsupervised neural networks for learning phases

Yuan Heng Tseng, Fu Jiun Jiang*

*此作品的通信作者

研究成果: 雜誌貢獻期刊論文同行評審

摘要

The impact on the performance of an unsupervised neural network (NN) for learning the phases of two-dimensional ferromagnetic Potts model, namely a deep learning autoencoder (AE), from using various training sets is investigated. We find that data below and in the vicinity of the transition temperature Tc are crucial in training a successful AE. Our results also indicate that the commonly employed training procedures for unsupervised NNs are not efficient, and the obtained outcomes here can be considered as useful guidelines to set up effective trainings for unsupervised NNs.

原文英語
文章編號105832
期刊Results in Physics
40
DOIs
出版狀態已發佈 - 2022 9月

ASJC Scopus subject areas

  • 物理與天文學 (全部)

指紋

深入研究「A comment on the training of unsupervised neural networks for learning phases」主題。共同形成了獨特的指紋。

引用此