Predicate Invention by Learning From Failures

04/29/2021
by   Andrew Cropper, et al.
0

Discovering novel high-level concepts is one of the most important steps needed for human-level AI. In inductive logic programming (ILP), discovering novel high-level concepts is known as predicate invention (PI). Although seen as crucial since the founding of ILP, PI is notoriously difficult and most ILP systems do not support it. In this paper, we introduce POPPI, an ILP system that formulates the PI problem as an answer set programming problem. Our experiments show that (i) PI can drastically improve learning performance when useful, (ii) PI is not too costly when unnecessary, and (iii) POPPI can substantially outperform existing ILP systems.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/21/2021

Inductive logic programming at 30

Inductive logic programming (ILP) is a form of logic-based machine learn...
02/20/2022

Learning logic programs by discovering where not to search

The goal of inductive logic programming (ILP) is to search for a hypothe...
09/15/2021

Parallel Constraint-Driven Inductive Logic Programming

Multi-core machines are ubiquitous. However, most inductive logic progra...
06/09/2011

Improving the Efficiency of Inductive Logic Programming Through the Use of Query Packs

Inductive logic programming, or relational learning, is a powerful parad...
11/28/2020

Discrete Math with Programming: A Principled Approach

Discrete mathematics is the foundation of computer science. It focuses o...
03/14/2012

Evolving Culture vs Local Minima

We propose a theory that relates difficulty of learning in deep architec...
07/09/2020

Concept Bottleneck Models

We seek to learn models that we can interact with using high-level conce...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.