Video URL
https://pirsa.org/23100032Correlations, representations and transformers in physics and in AI
Achim Kempf University of Waterloo
Abstract
I will begin by reviewing the general mathematical concept of representation. I will then show that representation theory is more generally applicable than one might expect, for example in quantum foundations, in quantum gravity and in machine learning. In those contexts, I will first talk about the notion of representation underlying phenomena of emergence in quantum gravity. I will then discuss how quantum reference frames might be viewed as representations. Finally, I will talk about how transformer models, such as GPT-4, construct representations of what they learn and, in that light, what it may take for machines to reach AGI or even consciousness.
---
Zoom link: https://pitp.zoom.us/j/99349397588?pwd=T056VjZXRWZWT28zY3VOZHFDcmQ3QT09