Extracting Refined Rules from Knowledge-Based Neural Networks

Machine Learning

Volumn 13, Issue 1, 1993, Pages 71-101

  Towell, Geoffrey G ^a,b   Shavlik, Jude W ^a  

^a UNIVERSITY OF WISCONSIN MADISON   (United States)

^b SIEMENS CORPORATE RESEARCH   (United States)

Author keywords

integrated learning; representational shift; rule extraction from neural networks; theory refinement

Indexed keywords

COMPUTER AIDED INSTRUCTION; KNOWLEDGE BASED SYSTEMS; NEURAL NETWORKS;

KNOWLEDGE BASED NEURAL NETWORKS; REFINED RULES;

LEARNING SYSTEMS;

EID: 0027678679     PISSN: 08856125     EISSN: 15730565     Source Type: Journal    
DOI: 10.1023/A:1022683529158     Document Type: Article

References (42)

1. Refinement of approximate reasoning-based controllers by reinforcement learaning
2. Extraction of semantic features and logical rules from a multilayer neural network
3. Learning relations from noisy examples: An empirical comparison of LINUS and FOIL
4. The cascade-correlation learning architecture
5. An empirical comparison of ID3 and backpropagation
6. Rule learning by searching on adapted nets
7. On the complexity of teaching
8. Analysis of E. coli promoter sequences
9. Compilation and analysis of escherichia coli promotor DNA sequences
10. A neural expert system with automated extraction of fuzzy if-then rules
11. Connectionist learning procedures
12. On the complexity of loading shallow neural networks
13. Effect of non-contacted bases on the affinity of 434 operator for 434 repressor and Cro
14. Optimal brain damage
15. R1: A rule-based configurer of computer systems
16. The connectionist scientist game: Rule extraction and refinement in a neural network
17. The magical number seven, plus or minus two: Some limits on our capacity for processing information
18. Skeletonization: A technique for trimming the fat from a network via relevance assessment
19. ID2-of-3: Constructive induction of M-of-N concepts for discriminators in decision trees
20. Hierarchies in concept attainment
21. Training knowledge-based neural networks to recognize genes in DNA sequences
22. Simplifying neural networks by soft weight-sharing
23. Changing the rules: A comprehensive approach to theory refinement
24. Direct transfer of learned information among neural networks
25. Simplifying decision trees
26. Learning internal representations by error propagation
27. Medical diagnostic expert system based on PDP model
28. Using multi-layered neural networks for learning symbolic knowledge
29. Symbolic and neural net learning algorithms: An empirical comparison
30. Consensus patterns in DNA
31. Two problems with backpropagation and other steepest descent learning procedures for networks
32. Using background knowledge in concept formation
33. Interpretation of artificial neural networks: Mapping knowledge-based neural networks into rules
34. Refinement of approximately correct domain theories by knowledge-based neural networks