Designing the network topology of feedforward neural network for scene illumination classification
Determining the topology of network as one of the objectives of ANN systems, is not following any certain rules or algorithms but still there are several hints which help us to restrict the neural network architecture set. Hence, the process of testing structures will be the solution of finding most...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Scientific Publishers
2017
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/61307/1/Designing%20the%20network%20topology%20of%20feedforward%20neural%20network%20for%20scene%20illumination%20classification.pdf http://psasir.upm.edu.my/id/eprint/61307/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Putra Malaysia |
| Language: | English |
| Summary: | Determining the topology of network as one of the objectives of ANN systems, is not following any certain rules or algorithms but still there are several hints which help us to restrict the neural network architecture set. Hence, the process of testing structures will be the solution of finding most effective one among a limited set. This study aims to apply testing method on scene illumination classification system to find out the appropriate ANN structure. The results of this study apply on similar classification systems to avoid redoing the testing process. |
|---|