Learning a phase diagram from dynamics

Time series data contains useful information on the phase of a system. Here we propose the use of recurrent neural networks (LSTM) to learn and extract such information in order to classify phases and locate phase boundaries. We demonstrate this on a many-body localized model, and attempt to interpret the learned behavior by looking at individual LSTM cells. We also discuss the validity of the learned model and investigate its limits.

Collection/Series: 
Event Type: 
Seminar
Scientific Area(s): 
Event Date: 
Monday, April 23, 2018 - 14:00 to 15:30
Location: 
Time Room
Room #: 
294