Can we trust phase diagrams produced by artificial neural networks?



Playing this video requires the latest flash player from Adobe.

Download link (right click and 'save-as') for playing in VLC or other compatible player.


Recording Details

Speaker(s): 
Collection/Series: 
PIRSA Number: 
19040090

Abstract

So far artificial neural networks have been applied to discover phase diagrams in many different physical models. However, none of these studies have revealed any fundamentally new physics. A major problem is that these neural networks are mainly considered as black box algorithms. On the journey to detect new physics it is important to interpret what artificial neural networks learn. On the one hand this allows us to judge whether to trust the results, and on the other hand this can give us insight to possible new physics. In this talk I will 
discuss applications to different models where we successfully interpreted what was learned by the neural networks.