Communications of the ACM
Learnability and the Vapnik-Chervonenkis dimension
Journal of the ACM (JACM)
Towards inductive generalisation in higher order logic
ML92 Proceedings of the ninth international workshop on Machine learning
Foundations of Inductive Logic Programming
Foundations of Inductive Logic Programming
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Learning Logical Definitions from Relations
Machine Learning
Learning Programs in the Event Calculus
ILP '97 Proceedings of the 7th International Workshop on Inductive Logic Programming
Logic and Learning
Extending the Soar Cognitive Architecture
Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference
ProbLog: a probabilistic prolog and its application in link discovery
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
Discovering rules by meta-level abduction
ILP'09 Proceedings of the 19th international conference on Inductive logic programming
Machine Learning
Random walk inference and learning in a large scale knowledge base
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Induction of the indirect effects of actions by monotonic methods
ILP'05 Proceedings of the 15th international conference on Inductive Logic Programming
The decidability of the first-order theory of knuth-bendix order
CADE' 20 Proceedings of the 20th international conference on Automated Deduction
Declarative modeling for machine learning and data mining
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
| Hi-index | 0.00 |
In recent years Predicate Invention has been under-explored within Inductive Logic Programming due to difficulties in formulating efficient search mechanisms. However, a recent paper demonstrated that both predicate invention and the learning of recursion can be efficiently implemented for regular and context-free grammars, by way of abduction with respect to a meta-interpreter. New predicate symbols are introduced as constants representing existentially quantified higher-order variables. In this paper we generalise the approach of Meta-Interpretive Learning (MIL) to that of learning higher-order dyadic datalog programs. We show that with an infinite signature the higher-order dyadic datalog class H22 has universal Turing expressivity though H22 is decidable given a finite signature. Additionally we show that Knuth-Bendix ordering of the hypothesis space together with logarithmic clause bounding allows our Dyadic MIL implementation MetagolD to PAC-learn minimal cardinailty H22 definitions. This result is consistent with our experiments which indicate that MetagolD efficiently learns compact H22 definitions involving predicate invention for robotic strategies and higher-order concepts in the NELL language learning domain.