Evaluation of the simplex method for training simple multilayer neural networks
A learning algorithm based on the modified Simplex method is proposed for training multilayer neural networks. This algorithm is tested for neural modelling of experimental results obtained during crossflow filtration tests. The Simplex method is compared to standard back-propagation. Simpler to implement, Simplex has allowed us to achieve better results over four different databases with lower calculation times. The Simplex algorithm is therefore of interest compared to the classical learning techniques for simple neural structures.
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | article biblioteca |
| Language: | eng |
| Subjects: | U10 - Informatique, mathématiques et statistiques, Q02 - Traitement et conservation des produits alimentaires, modèle mathématique, écoulement de fluide, filtration, application des ordinateurs, http://aims.fao.org/aos/agrovoc/c_24199, http://aims.fao.org/aos/agrovoc/c_25441, http://aims.fao.org/aos/agrovoc/c_2900, http://aims.fao.org/aos/agrovoc/c_24009, |
| Online Access: | http://agritrop.cirad.fr/390554/ http://agritrop.cirad.fr/390554/1/390554.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|