Corpus ID: 11138624

Avoiding Pitfalls When Learning Recursive Theories

@inproceedings{CameronJones1993AvoidingPW,
  title={Avoiding Pitfalls When Learning Recursive Theories},
  author={R. Cameron-Jones and J. R. Quinlan},
  booktitle={IJCAI},
  year={1993}
}
Learning systems that express theories in rst-order logic must ensure that the theories are executable and, in particular, that they do not lead to innnite recursion. This paper presents a heuristic method for preventing innnite re-cursion in the (multi-clause) deenition of a recursive relation. The method has been implemented in the latest version of foil, but could also be used with any learning method that grows clauses from ground facts by repeated specialization. Results on several… Expand
Learning Recursive Theories in the Normal ILP Setting
  • D. Malerba
  • Computer Science, Mathematics
  • Fundam. Informaticae
  • 2003
TLDR
Computational solutions to some relevant issues raised by the multiple predicate learning problem are proposed and the proposed approach has been implemented in the ILP system ATRE and tested on some laboratory-sized and real-world data sets. Expand
Induction of Recursive Theories in the Normal ILP Setting: Issues and Solutions
TLDR
Computational solutions to some relevant issues raised by the multiple predicate learning problem are proposed and implemented in the ILP system ATRE and tested in the specific context of the document understanding problem within the WISDOM project. Expand
Inductive Learning of Normal Clauses
TLDR
The classical constraint: the learned program must cover the positive examples and reject the negative ones, can be too strong and a weaker criterion is defined: it is required that a positive example is not considered as False (resp. True) by the learning program. Expand
Induction of logic programs: FOIL and related systems
TLDR
This paper provides an overview of the principal ideas and methods used in the current version of the FOIL system, including two recent additions. Expand
A three-valued framework for the induction of general logic programs
TLDR
A framework to learn general logic programs, i.e., sets of rules which may contain negation in their bodies, is presented, based on a three-valued logic that enables to model both the notion of unknown information and the idea of undeened answer of the Prolog interpreter. Expand
Induction of contraint logic
Inductive Logic Programming is mainly concerned with the problem of learning concept deenitions from positive and negative examples of these concepts and background knowledge. Because of complexityExpand
A bidirectional ILP algorithm
The paper presents an approach for using a bidirectional search strategy for inductively learning clauses in a restricted first-order language. The learning target is to find a set of goal clausesExpand
Advantages of decision lists and implicit negatives in Inductive Logic Programming
TLDR
Tests with a selection of list-processing problems from Bratko’s introductory Prolog text demonstrate that the combination of implicit negatives and intensionality allowfoidl to learn correct programs from far fewer examples thanfoil. Expand
Induction of Constraint Logic Programs
TLDR
A new approach for learning logic programs containing function symbols other than constants is proposed, to consider a domain that enables to interpret the function symbols and to compute the interest of a given value for discriminating positive and negative examples. Expand
An ILP Method Based on Instance Graph
TLDR
In this opinion, FOIL should memory more of previous learning to help further search in rule space, and invented instance graph H(R,E), where R is a ruleset and E is an instance space. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 10 REFERENCES
Determinate Literals in Inductive Logic Programming
TLDR
Key ideas from FOIL and GOLEM are sketched and the use of determinate literals in a greedy search context is discussed and the efficacy of this approach is illustrated on the task of learning the quicksort procedure and other small but non-trivial list-manipulation functions. Expand
Machine Invention of First Order Predicates by Inverting Resolution
TLDR
A mechanism for automatically inventing and generalising first-order Horn clause predicates is presented and implemented in a system called CIGOL, which uses incremental induction to augment incomplete clausal theories. Expand
Algorithmic Program Debugging
TLDR
An algorithm that can fix a bug that has been identified, and integrate it with the diagnosis algorithms to form an interactive debugging system that can debug programs that are too complex for the Model Inference System to synthesize. Expand
A Knowledge-intensive Approach to Learning Relational Concepts
TLDR
Providing domain knowledge to the integrated system can decrease the amount of search required during learning and increase the accuracy of learned concepts, even when the domain knowledge is incorrect and incomplete. Expand
Pazzani and Dennis Kibler . The utility of knowledge in inductivelearning
  • Machine Learning
  • 1992
Determinate literals ininductive logic programming
  • 1991
Learning logical de nitions from relations
  • Machine Learning
  • 1990
Stephen Muggleton and Cao Feng. EEcient induction of logic programs
  • Proceedings First Conference on Algorithmic Learning Theory
  • 1990
Completeness for induction procedures
  • Proceedings Eighth International Workshop on Machine Learning
Learning logical deenitions from relations
  • Machine Learning