[2005.10505] Reveal flocking of birds flying in fog by machine learningopen searchopen navigation menucontact arXivarXiv Twitter

We study the first-order flocking transition of birds flying in low-visibility conditions by employing three different representative types of neural network (NN) based machine learning architectures that are trained via either an unsupervised learning approach called "learning by confusion" or a widely used supervised learning approach. We find that after the training via either the unsupervised learning approach or the supervised learning one, all of these three different representative types of NNs, namely, the fully-connected NN, the convolutional NN, and the residual NN, are able to successfully identify the first-order flocking transition point of this nonequilibrium many-body system. This indicates that NN based machine learning can be employed as a promising generic tool to investigate rich physics in scenarios associated to first-order phase transitions and nonequilibrium many-body systems.

1 mentions: @tjmlab
Date: 2020/05/23 18:52

Related Entries

Read more [2002.07266] Predicting new superconductors and their critical temperatures using unsupervised machi...
0 users, 1 mentions 2020/02/19 03:50
Read more [2003.02888] Competing pairing interactions responsible for the large upper critical field in a stoi...
0 users, 1 mentions 2020/03/09 08:21
Read more [2003.06295] Experimental demonstration and analysis of random field effects in ferromagnet/antiferr...
0 users, 1 mentions 2020/03/16 03:50
Read more [2003.07081] Field-induced phase transitions of the Kitaev material $α$-RuCl$_3$ probed by thermal e...
0 users, 1 mentions 2020/03/17 03:50
Read more [2004.14766] Machine learning materials properties for small datasetsopen searchopen navigation menu...
0 users, 1 mentions 2020/05/01 02:21
Read more [2005.10507] Gaussian process analysis of Electron Energy Loss Spectroscopy (EELS) data: parallel re...
0 users, 1 mentions 2020/05/22 05:21