top | item 12896182

Tensorflow Deepmath: Experiments towards neural network theorem proving

142 points| runesoerensen | 9 years ago |github.com

12 comments

order
[+] bitL|9 years ago|reply
What logic does it use? Any chance using relevance or linear logic to avoid vacuous truth proofs (like in set theory)?
[+] cmrx64|9 years ago|reply
It's currently integrating higher-order logic (HOL) with a reimplementation of HOL Light.
[+] Mao_Zedang|9 years ago|reply
Hook it up to a network that makes theorems.
[+] SticksAndBreaks|9 years ago|reply
Every problem i can break into a sub problem is solveable. Thus proofen by induction that i can break recursively down every problem, i deduce- that i crashed with a NN-Stackoverflow.
[+] thomasahle|9 years ago|reply
> Every problem i can break into a sub problem is solveable.

Given the sub problems are either solvable or can in turn be broken down, I suppose?