>
> More importantly, how does logic in Hilbert space solve any existing
> problems? How does it get us closer to AGI?

The papers I recall from YKY center around the desire to incorporate
logic in some kind of flexible, modern structure that tends towards
neuro-symbolic. I've recollect descriptions of logic with Word2Vec,
transformers, and now Hilbert space (admittedly I don't yet grasp the
details!).

I think it's a good goal if you believe (as I do) that it's a good
idea to have reliable and explainable logic while pursuing some means
of handling the combinatorial explosion / curse of dimensionality
problem.

Mike A


------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T54594b98b5b98f83-Md440fb1d7242a9b0244bcf8a
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to