DeepAI AI Chat
Log In Sign Up

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

by   Po-Wei Wang, et al.

Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems. In this paper, we propose a new direction toward this goal by introducing a differentiable (smoothed) maximum satisfiability (MAXSAT) solver that can be integrated into the loop of larger deep learning systems. Our (approximate) solver is based upon a fast coordinate descent approach to solving the semidefinite program (SDP) associated with the MAXSAT problem. We show how to analytically differentiate through the solution to this SDP and efficiently solve the associated backward pass. We demonstrate that by integrating this solver into end-to-end learning systems, we can learn the logical structure of challenging problems in a minimally supervised fashion. In particular, we show that we can learn the parity function using single-bit supervision (a traditionally hard task for deep networks) and learn how to play 9x9 Sudoku solely from examples. We also solve a "visual Sudok" problem that maps images of Sudoku puzzles to their associated logical solutions by combining our MAXSAT solver with a traditional convolutional architecture. Our approach thus shows promise in integrating logical structures within deep learning.


page 1

page 2

page 3

page 4


End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking

Machine learning systems perform well on pattern matching tasks, but the...

Learning Modulo Theories

Recent techniques that integrate solver layers into Deep Neural Networks...

Geometrization of deep networks for the interpretability of deep learning systems

How to understand deep learning systems remains an open problem. In this...

Learning Symmetric Rules with SATNet

SATNet is a differentiable constraint solver with a custom backpropagati...

Modern Machine and Deep Learning Systems as a way to achieve Man-Computer Symbiosis

Man-Computer Symbiosis (MCS) was originally envisioned by the famous com...

Techniques for Symbol Grounding with SATNet

Many experts argue that the future of artificial intelligence is limited...

Physarum Powered Differentiable Linear Programming Layers and Applications

Consider a learning algorithm, which involves an internal call to an opt...