Dynamically adding symbolically meaningful nodes to knowledge-based neural networks

Knowledge-Based Systems

Volumn 8, Issue 6, 1995, Pages 301-311

  Pitz, David W ^a   Shavlik, Jude W ^a  

^a UNIVERSITY OF WISCONSIN MADISON   (United States)

Author keywords

computational biology; KBANN algorithm; network growing algorithms; theory refinement

Indexed keywords

ALGORITHMS; BIOLOGY; COMPUTATION THEORY; DATA STRUCTURES; DIGITAL ARITHMETIC; HEURISTIC METHODS; INFERENCE ENGINES; KNOWLEDGE BASED SYSTEMS; LEARNING SYSTEMS; NATURAL SCIENCES COMPUTING;

COMPUTATIONAL BIOLOGY; DOMAIN THEORY; KNOWLEDGE BASED NEURAL NETWORKS; NETWORK GROWING ALGORITHMS; REAL WORLD PROBLEMS; THEORY REFINEMENT;

NEURAL NETWORKS;

EID: 0029505748     PISSN: 09507051     EISSN: None     Source Type: Journal    
DOI: 10.1016/0950-7051(96)81915-0     Document Type: Article

References (35)

1. Theory reduction, theory revision, and retranslation
2. The utility of knowledge in inductive learning
3. Theory refinement combining analytical and empirical methods
4. Knowledge-based artificial neural networks
5. Integration of neural heuristics into knowledge-based inference
6. Symbolic Knowledge and Neural Networks: Insertion. Refinement, and Extraction
7. Back-propagation learning in expert networks
8. Network structuring and training using rule-based knowledge
9. Combining connectionist and symbolic learning to refine certainty-factor rule-bases
10. Using symbolic learning to improve knowledge-based neural networks
11. Extracting refined rules from knowledge-based neural networks
12. The cascade-correlation learning architecture
13. Learning in feedforward layered networks the tiling algorithm
14. The upstart algorithm a method for constructing and training feedforward neural networks
15. Learning internal representations by error propagation
16. Learning structural descriptions from examples
17. Learning distributed representations of concepts
18. Generalization by weight-elimination with application to forecasting
19. Training knowledge-based neural networks to recognize genes in DNA sequences
20. Machine learning approaches to gene recognition
21. Optimization by simulated annealing
22. Using genetic search to refine knowledge-based neural networks
23. A practical Bayesian framework for backpropagation networks
24. A universal prior for integers and estimation by minimum description length
25. The effective number of parameters: an analysis of generalization and regularization in nonlinear learning systems
26. Rule learning by searching on adapted nets
27. The connectionist scientist game: rule extraction and refinement in a neural network
28. Combining prior symbolic knowledge and constructive neural network learning
29. Constructing hidden units using examples and queries
30. Training second-order recurrent neural networks using hints
31. Using knowledge-based neural networks to improve algorithms: refining the Chou-Fasman algorithm for protein folding
32. Neural control for rolling mills: incorporating domain theories to overcome data deficiency
33. Refining PID controllers using neural networks
34. Heuristically expanding knowledge-based neural networks