Survey and critique of techniques for extracting rules from trained artificial neural networks

Knowledge-Based Systems

Volumn 8, Issue 6, 1995, Pages 373-389

  Andrews, Robert ^a   Diederich, Joachim ^a   Tickle, Alan B ^a  

^a QUEENSLAND UNIVERSITY OF TECHNOLOGY   (Australia)

Author keywords

fuzzy neural networks; inferencing; knowledge insertion; rule extraction; rule refinement

Indexed keywords

FUZZY NEURAL NETWORKS; INFERENCING; KNOWLEDGE INSERTION; RULE CONFINEMENT; RULES EXTRACTION; TAXONOMY;

FUZZY SETS; INFERENCE ENGINES; KNOWLEDGE ACQUISITION; KNOWLEDGE ENGINEERING; LEARNING ALGORITHMS; LEARNING SYSTEMS; NEURAL NETWORKS;

KNOWLEDGE BASED SYSTEMS;

EID: 0029484103     PISSN: 09507051     EISSN: None     Source Type: Journal    
DOI: 10.1016/0950-7051(96)81920-4     Document Type: Article

References (37)

1. Extracting provably correct rules from artificial neural networks
2. The extraction of refined rules from knowledge based neural networks
3. The cascade-correlation learning architecture
4. Extraction insertion and refinement of symbolic rules in dynamically driven recurrent networks
5. Learning and extracting finite state automata with second-order recurrent neural networks
6. Induction of finite-state languages using second-order recurrent networks
7. Connectionist expert systems
8. Production rules as a representation for a knowledge-based consultation program
9. Explanation and dialogue
10. A reactive approach to explanation in expert and advice-giving systems
11. A reactive approach to explanation
12. Using sampling and queries to extract rules from trained neural networks
13. Medical diagnostic; expert system based on PDP model
14. The use of sub-symbolic methods for the automation of knowledge acquisition for expert systems
15. The MONK's problems: a performance comparison of different learning algorithms
16. Rule refinement with recurrent neural networks
17. Optimised rule induction
18. Extraction of semantic features and logical rules from a multilayer neural network
19. Rule learning by searching on adapted nets
20. Rule generation from neural networks
21. Inserting and extracting knowledge from constrained error back propagation networks
22. The connectionist scientist game: rule extraction and refinement in a neural network
23. Adaptive mixtures of local experts
24. Network structuring and training using rule-based knowledge
25. Rule extraction from a constrained error back propagation MLP
26. Automated knowledge acquisition of rules with continuously valued attributes
27. On fuzzy modeling using fuzzy neural networks with the back-propagation algorithm
28. Neurofuzzy systems - fuzzy inference using a structured neural network
29. Refinement of approximate reasoning-based controllers by reinforcement learning
30. Neural networks in designing fuzzy systems for real world applications
31. Fuzzy MLP based expert system for medical diagnosis
32. Knowledge based neural network - using fuzzy logic to initialise a multilayered neural network and interpret postlearning results
33. Heuristics for the extraction of rules from discrete time recurrent neural networks