I don't work in the field so I'm probably just repeating something Hinton already said, but it seems to me like attempting to model things in reality that have graph-like structures (like interacting pairs of residues in a 3d protein structure) using sequences with finite context lengths is ultimately going to be less efficient than modelling graphs. My guess is this work is roughly describing that I think of: https://www.cis.upenn.edu/~mkearns/papers/barbados/jordan-tu...
it could also be I completely misunderstand context in sequential models and what I'm describing is already being used, or has been evaluated and has been unsuccessful.
dekhn|1 year ago
it could also be I completely misunderstand context in sequential models and what I'm describing is already being used, or has been evaluated and has been unsuccessful.