Papers of the day   All papers

SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver

Comments

May 30 2019 Po-Wei Wang

1/ Integrate logic and deep learning with #SATNet, a differentiable SAT solver! #icml2019 Paper: https://arxiv.org/abs/1905.12149 Code: https://github.com/locuslab/SATNet Joint work with @priyald17, Bryan Wilder, and @zicokolter. https://t.co/YuVGHytMaV
3 replies, 377 likes


May 30 2019 Zico Kolter

New work with @_powei, @priyald17, and Bryan Wilder on (SDP-based, differentiable, approximate) SAT solving as a layer within deep networks. For example, learns to play 9x9 Sudoku just from examples, without any structure provided (past work like OptNet never scaled beyond 4x4).
2 replies, 131 likes


Jun 11 2019 Priya L. Donti

Excited to have received a best paper honorable mention for our paper "SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver" (with @_powei, Bryan Wilder, and @zicokolter) at #ICML2019! https://t.co/UY2rIX5to9
3 replies, 44 likes


Jun 11 2019 Zico Kolter

Congrats to @_powei, @priyald17, and Bryan on our best paper honorable mention at #icml2019! Come see our talk at 4:40pm in Hall A. Paper: https://arxiv.org/abs/1905.12149 Code: https://github.com/locuslab/SATNet
0 replies, 18 likes


May 30 2019 Priya L. Donti

Check out #SATNet, our upcoming #icml2019 paper (with @_powei, Bryan Wilder, and @zicokolter). By putting a(n approximate) differentiable MAXSAT solver into a neural network, we're able to solve 9x9 Sudoku (original, and from images --> solutions) solely from examples!
0 replies, 4 likes


Jun 29 2019 Jekejeke Prolog

SATNet: Bridging deep learning and logical reasoning - Wang et al., 2019 https://arxiv.org/abs/1905.12149
0 replies, 1 likes


Content