Differentiable Inductive Logic Programming in High-Dimensional Space

08/13/2022
by   Stanisław J. Purgał, et al.
0

Synthesizing large logic programs through Inductive Logic Programming (ILP) typically requires intermediate definitions. However, cluttering the hypothesis space with intensional predicates often degrades performance. In contrast, gradient descent provides an efficient way to find solutions within such high-dimensional spaces. Neuro-symbolic ILP approaches have not fully exploited this so far. We propose an approach to ILP-based synthesis benefiting from large-scale predicate invention exploiting the efficacy of high-dimensional gradient descent. We find symbolic solutions containing upwards of ten auxiliary definitions. This is beyond the achievements of existing neuro-symbolic ILP systems, thus constituting a milestone in the field.

READ FULL TEXT
research
04/26/2023

The Logic of Logic Programming

Our position is that logic programming is not programming in the Horn cl...
research
04/11/2018

Completeness of Cyclic Proofs for Symbolic Heaps

Separation logic is successful for software verification in both theory ...
research
08/30/2023

Deep Inductive Logic Programming meets Reinforcement Learning

One approach to explaining the hierarchical levels of understanding with...
research
04/26/2019

Neural Logic Machines

We propose the Neural Logic Machine (NLM), a neural-symbolic architectur...
research
11/13/2017

Learning Explanatory Rules from Noisy Data

Artificial Neural Networks are powerful function approximators capable o...
research
12/20/2014

Explorations on high dimensional landscapes

Finding minima of a real valued non-convex function over a high dimensio...
research
03/02/2021

Differentiable Inductive Logic Programming for Structured Examples

The differentiable implementation of logic yields a seamless combination...

Please sign up or login with your details

Forgot password? Click here to reset