A new method to evaluate a trained artificial neural network
In comparison with traditional local sample testing methods, this paper proposes a new approach to evaluate a trained neural network. A new parameter is defined to identify the different potential roles of the individual input factors based on the trained connections of the nodes in the network. Com...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Default Conference proceeding |
| Published: |
2001
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/2134/4122 |
| Tags: | Add Tag |