Advantages of Hierarchical Organisation in Neural Networks
p. 48-60
Résumé
Artificial neural networks, which are inspired by the structure and functioning of the vertebrate-brain, are powerful modelling tools. However, the black-box representation they provide does not allow the usage of the huge accumulation of theoretical knowledge on system dynamics. Similarly, they also do not seem to provide any clue for the symbolic operations typical for the higher functioning mode of the human brain.
In this study a "chaos control" problem is used as a test case to demonstrate the viability of extracting an analytical model from an artificial neural network. The results are used to comment on the advantages of hierarchical organisation not only in artificial but also natural neural networks.
Texte
Citer cet article
Référence papier
Yagmur Denizhan et Gursel Karacor, « Advantages of Hierarchical Organisation in Neural Networks », CASYS, 16 | 2004, 48-60.
Référence électronique
Yagmur Denizhan et Gursel Karacor, « Advantages of Hierarchical Organisation in Neural Networks », CASYS [En ligne], 16 | 2004, mis en ligne le 01 August 2024, consulté le 20 September 2024. URL : http://popups.lib.uliege.be/1373-5411/index.php?id=2330
Auteurs
Yagmur Denizhan
Department of Electrical and Electronics Engineering, Bogazici University, 80815, Bebek, Istanbul, Turkey
Gursel Karacor
Department of Computer Engineering, Turkish Airforce Academy, Yesilyurt, Istanbul, Turkey