Rule generation from neural networks
Journal Article
·
· IEEE Transactions on Systems, Man, and Cybernetics
OSTI ID:135309
- Univ. of Florida, Gainesville, FL (United States)
The neural network approach has proven useful for the development of artificial intelligence systems. However, a disadvantage with this approach is that the knowledge embedded in the neural network is opaque. In this paper, we show how to interpret neural network knowledge in symbolic form. We lay down required definitions for this treatment, formulate the interpretation algorithm, and formally verify its soundness. The main result is a formalized relationship between a neural network and a rule-based system. In addition, it has been demonstrated that the neural network generates rules of better performance than the decision tree approach in noisy conditions. 7 refs.
- OSTI ID:
- 135309
- Journal Information:
- IEEE Transactions on Systems, Man, and Cybernetics, Vol. 24, Issue 8; Other Information: PBD: Aug 1994
- Country of Publication:
- United States
- Language:
- English
Similar Records
Development of HT-BP nueral network system for the identification of well test interpretation model
A comparison of expert systems and neural networks applications in power generation
Development of the HT-BP neural network system for the identification of a well-test interpretation model
Conference
·
Sun Dec 31 00:00:00 EST 1995
·
OSTI ID:135309
A comparison of expert systems and neural networks applications in power generation
Conference
·
Sat Dec 31 00:00:00 EST 1994
·
OSTI ID:135309
Development of the HT-BP neural network system for the identification of a well-test interpretation model
Journal Article
·
Thu Aug 01 00:00:00 EDT 1996
· SPE Computer Applications
·
OSTI ID:135309
+1 more