|
Abstract
|
|
|---|---|
| This work presents a new method to solve the nowadays problems about the symbolic knowledge acquisition from the weights of a neural network. It can be divided into two sections. The former corresponds to the framework whose idea is to support knowledge acquisition, where the optimum way of training the neural network is related with the knowledge that can be acquired. The relationship among the knowledge stored in the weights and the new implemented method to acquire rules from the weights is explained. The latter stage is a method to decide the rule to trigger for a new prediction. | |
|
International
|
Si |
|
Congress
|
4th International ISKE Conference on Intelligent Systems and Knowledge Engineering |
|
|
960 |
|
Place
|
university of Hasselt (Belgica) |
|
Reviewers
|
Si |
|
ISBN/ISSN
|
981-4295-05-1 |
|
|
10.1142/9789814295062_0007 |
|
Start Date
|
27/11/2009 |
|
End Date
|
28/11/2009 |
|
From page
|
46 |
|
To page
|
51 |
|
|
INTELLIGENT DECISION MAKING SYSTEMS Proceedings of the 4th International ISKE Conference on Intelligent Systems and Knowledge Engineering World Scientific Proceedings Series on Computer Engineering and Information Science - Vol. 2 |