Thursday, 19th of November 2020, 12:00 – 1:00

Universality in spin models, automata, and neural networks


 Gemma De las Cuevas
Department of Theoretical Physics, University of Innsbruck


Why is it so easy to generate complexity? I will argue that this is due to the phenomenon of universality — essentially every non-trivial system is universal, and thus able to explore all complexity in its domain. We understand the phenomenon of universality in spin models, automata and neural networks. I will explain the first step toward rigorously linking the first two. I will also talk about one of the consequences of universality, namely undecidability. 


Nach oben scrollen