DeepMath - Deep Sequence Models for Premise Selection · HackerPapers discussions

DeepMath - Deep Sequence Models for Premise Selection — 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.

DeepMath - Deep Sequence Models for Premise Selection — mentioned by jackhoy

Mon, 27 Feb 2017 13:18:05 GMT

This seems to be relevant for premise selection https://arxiv.org/pdf/1606.04442.pdf but not found anything yet on premise collection

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

DeepMath - Deep Sequence Models for Premise Selection — mentioned by danblick

Tue, 08 Nov 2016 02:58:00 GMT

Check out the "Deepmath" paper linked above. (The paper is from a few months ago, the source code is new IIUC.) https://arxiv.org/abs/1606.04442

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

DeepMath - Deep Sequence Models for Premise Selection — mentioned by aab0

Fri, 15 Jul 2016 20:44:01 GMT

It seems kind of strange that he never thought of using computer proof systems for checking whether his proofs were right in class, and that he took a pattern-matching approach rather than using any of the existing AI proof-deriving systems like https://arxiv.org/abs/1606.04442 or https://intelligence.org/2013/12/21/josef-urban-on-machine-l...

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

DeepMath - Deep Sequence Models for Premise Selection — HN submission

Mon, 04 Jul 2016 15:21:06 GMT

DeepMath – Deep Sequence Models for Premise Selection

79 points; 14 discussion replies on HN. Paper and source history. A submission is not an endorsement.