DeepAI
Log In Sign Up

DeepStochLog: Neural Stochastic Logic Programming

06/23/2021
by   Thomas Winters, et al.
0

Recent advances in neural symbolic learning, such as DeepProbLog, extend probabilistic logic programs with neural predicates. Like graphical models, these probabilistic logic programs define a probability distribution over possible worlds, for which inference is computationally hard. We propose DeepStochLog, an alternative neural symbolic framework based on stochastic definite clause grammars, a type of stochastic logic program, which defines a probability distribution over possible derivations. More specifically, we introduce neural grammar rules into stochastic definite clause grammars to create a framework that can be trained end-to-end. We show that inference and learning in neural stochastic logic programming scale much better than for neural probabilistic logic programs. Furthermore, the experimental evaluation shows that DeepStochLog achieves state-of-the-art results on challenging neural symbolic learning tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/28/2018

DeepProbLog: Neural Probabilistic Logic Programming

We introduce DeepProbLog, a probabilistic logic programming language tha...
06/09/2011

Parameter Learning of Logic Programs for Symbolic-Statistical Modeling

We propose a logical/mathematical framework for statistical parameter le...
06/02/2015

Stochastic And-Or Grammars: A Unified Framework and Logic Perspective

Stochastic And-Or grammars (AOG) extend traditional stochastic grammars ...
10/07/2021

SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming

The goal of combining the robustness of neural networks and the expressi...
01/04/2017

Stochastic Planning and Lifted Inference

Lifted probabilistic inference (Poole, 2003) and symbolic dynamic progra...
11/11/2021

Towards Axiomatic, Hierarchical, and Symbolic Explanation for Deep Models

This paper proposes a hierarchical and symbolic And-Or graph (AOG) to ob...
04/25/2013

Inference and learning in probabilistic logic programs using weighted Boolean formulas

Probabilistic logic programs are logic programs in which some of the fac...