Relational program synthesis with numerical reasoning

Our approach can identify numerical values in linear arithmetic fragments, such as real difference logic, and from infinite domains, such as real numbers or integers.

no code implementations24 Aug 2022,

Inductive logic programming is a form of machine learning based on mathematical logic that generates logic programs from given examples and background knowledge.

Learning programs with magic values

1 code implementation5 Aug 2022,

A magic value in a program is a constant symbol that is essential for the execution of the program but has no clear explanation for its choice.

12

Learning programs by combining programs

no code implementations1 Jun 2022

The goal of inductive logic programming is to induce a set of rules (a logic program) that generalises examples.

Learning logic programs by discovering where not to search

no code implementations20 Feb 2022,

We use the constraints to bootstrap a constraint-driven ILP system.

Learning logic programs through divide, constrain, and conquer

1 code implementation16 Sep 2021

We introduce an inductive logic programming approach that combines classical divide-and-conquer search with modern constraint-driven search.

1

Parallel Constraint-Driven Inductive Logic Programming

Multi-core machines are ubiquitous.

Predicate Invention by Learning From Failures

no code implementations29 Apr 2021,

Discovering novel high-level concepts is one of the most important steps needed for human-level AI.

Inductive logic programming at 30

Inductive logic programming (ILP) is a form of logic-based machine learning.

Learning Logic Programs by Explaining Failures

no code implementations18 Feb 2021,

We introduce a technique for failure explanation based on analysing SLD-trees.

Inductive logic programming at 30: a new introduction

1 code implementation18 Aug 2020,

Inductive logic programming (ILP) is a form of machine learning.

12

Learning programs by learning from failures

no code implementations5 May 2020,

In this approach, an ILP system (the learner) decomposes the learning problem into three separate stages: generate, test, and constrain.

Knowledge Refactoring for Inductive Program Synthesis

We introduce the \textit{knowledge refactoring} problem, where the goal is to restructure a learner's knowledge base to reduce its size and to minimise redundancy in it.

2

Learning large logic programs by going beyond entailment

no code implementations21 Apr 2020,

We argue that a key limitation of existing systems is that they use entailment to guide the hypothesis search.

Turning 30: New Ideas in Inductive Logic Programming

Common criticisms of state-of-the-art machine learning include poor generalisation, a lack of interpretability, and a need for large amounts of training data.

Forgetting to learn logic programs

2 code implementations15 Nov 2019

To improve learning performance, we explore the idea of forgetting, where a learner can additionally remove programs from its BK.

188

Logical reduction of metarules

no code implementations25 Jul 2019,

In general, derivation reduced sets of metarules outperforms subsumption and entailment reduced sets, both in terms of predictive accuracies and learning times.

Learning higher-order logic programs

Our theoretical results show that learning higher-order programs, rather than first-order programs, can reduce the textual complexity required to express programs which in turn reduces the size of the hypothesis space and sample complexity.

188

Inductive general game playing

2 code implementations23 Jun 2019, ,

This problem is central to inductive general game playing (IGGP).

5

Playgol: learning programs through play

1 code implementation18 Apr 2019

In this approach, a program induction system (the learner) is given a set of tasks and initial background knowledge.

188
Cannot find the paper you are looking for? You can Submit a new open access paper.