End-to-End Differentiable Proving · HackerPapers discussions

End-to-End Differentiable Proving — mentioned by popinman322

Mon, 19 Oct 2020 07:10:03 GMT

IIRC these nets don't actually build a knowledge base (though I may be wrong, it's been a while). They're still functioning in lossy continuous space. This is probably fine with a low number of symbols and relations, but once you get to the level of a neural theorem prover you need to properly handle symbol binding. If I'm working with integers and integer-valued variables, how do I represent the variables? How do I represent the operations? This gets more complex once you leave a closed domain, where all the operations and variables are defined up front, and you enter an open domain like…

Paper and discussion history. A mention is not an endorsement.

End-to-End Differentiable Proving — mentioned by maffydub

Tue, 06 Jun 2017 14:18:34 GMT

I recently went to a talk at the London Machine Learning meetup (https://www.meetup.com/London-Machine-Learning-Meetup/) on "End-to-end Differentiable Proving" (https://arxiv.org/abs/1705.11040). Basically, this was about building neural networks based on propositional logic (e.g. Prolog-style statements), which was how some traditional expert systems were built. Unfortunately, there wasn't a video of the presentation, and I can't find the slides anywhere. If you're based around London, the London Machine Learning meetups are always worth attending!

Paper and discussion history. A mention is not an endorsement.