Approximate match of rules using backpropagation neural networks

Machine Learning

Volumn 44, Issue 3, 2001, Pages 273-299

  Kijsirikul, Boonserm ^a   Sinthupinyo, Sukree ^a   Chongkasemwongse, Kongsak ^a  

^a CHULALONGKORN UNIVERSITY   (Thailand)

Author keywords

Approximate match; Backpropagation neural networks; Feature generation; Inductive logic programming

Indexed keywords

APPROXIMATION THEORY; BACKPROPAGATION; DATABASE SYSTEMS; LEARNING SYSTEMS; MULTI AGENT SYSTEMS; NEURAL NETWORKS; PATTERN MATCHING; TREES (MATHEMATICS);

LEARNING DOMAINS;

LOGIC PROGRAMMING;

EID: 0035451550     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1010976022223     Document Type: Article

References (32)

1. Multiple predicate learning with RTL
2. FONN: Combining first order logic with connectionist learning
3. Exploiting algorithm sketches in ILP
4. The CN2 induction algorithm
5. A knowledge base for finite element mesh design
6. The application of inductive logic programming to finite element mesh design
7. Applying ILP to diterpene structure elucidation from 13C NMR spectra
8. IBC: A first-order Bayesian classifier
9. Fossil: A robust relational learner
10. Controlling the complexity of learning in logic through syntactic and task-oriented models
11. Approximate ILP rules by backpropagation neural network: A result on Thai character recognition
12. A study of relevance for learning in deductive databases
13. Comparing methods for refining certainty-factor rule-bases
14. MULT_ICN: An empirical multiple predicate learner
15. Inductive logic programming
16. Inverse entailment and PROGOL
17. An experimental comparison of human and machine learning algorithms
18. Efficient induction of logic programs
19. Inductive logic programming: Theory and methods
20. A note on inductive generalization
21. Learning logical definitions from relations
22. Inductive constraint logic
23. Learning internal representations by error propagation
24. Theories for mutagenicity: A study in first-order and feature-based induction
25. Representing biases for inductive logic programming
26. Knowledge-based artificial neural networks