61–68 of 68 posts
Ever since I learned about category theory and its relationship with symbolic reasoning I've suspected that AGI will come from elegantly combining symbolic reasoning and probabilistic reasoning. This is the first project I've seen that seems to be positioned that way. Very cool.
There is a long history of efforts to combine symbolic and connectionist approaches. This is hardly the first!
Ever since I learned about category theory and its relationship with symbolic reasoning I've suspected that AGI will come from elegantly combining symbolic reasoning and probabilistic reasoning. This is the first project I've seen that seems to be positioned that way. Very cool.
> The work uses graphs developed using methods inspired by category theory as a central mechanism to teach the model to understand symbolic relationships in science.
https://news.mit.edu/2024/graph-based-ai-model-maps-future-i...
Ever since I learned about category theory and its relationship with symbolic reasoning I've suspected that AGI will come from elegantly combining symbolic reasoning and probabilistic reasoning. This is the first project I've seen that seems to be positioned that way. Very cool.
How does Scallop scale on large knowledge bases (KBs) for doing probabilistic reasoning? I'm currently working on large KB with ~ 12M facts and trying to do probabilistic inference on it. So far I've been using [cplint]( https://friguzzi.github.io/cplint/_build/html/index.html ) which is based on SWI-Prolog. It works fine for toy examples, however, it doesn't finish running for the large KB - even after waiting for i…
I am surprised you have problems with 12M facts and can't process them in a week, looks like bug in software you are using.
Earlier quoted context omitted.
I am surprised you have problems with 12M facts and can't process them in a week, looks like bug in software you are using.
Thanks for the comment. Have you run cplint on a kb of the similar size before and gotten it to finish in reasonable time?
Ever since I learned about category theory and its relationship with symbolic reasoning I've suspected that AGI will come from elegantly combining symbolic reasoning and probabilistic reasoning. This is the first project I've seen that seems to be positioned that way. Very cool.
I know a tiny bit about category theory but nothing about symbolic reasoning. Would anyone mind ELI5ing the connection between the two?
Category theory can be leveraged to make faster theorem provers (making complex symbolic reasoning practical at larger scales).
Don't ask me how, hopefully someone who studies it will chime in and correct me / expand.
Earlier quoted context omitted.
Thanks for the comment. Have you run cplint on a kb of the similar size before and gotten it to finish in reasonable time?
I never used cplint, but I use other software (including I built myself) to process KBs with many billions of facts.