View(s) :
1 (0 ULiège)
Download(s) :
16 (0 ULiège)
Abstract
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.
Text
References
Bibliographical reference
Yagmur Denizhan and Gursel Karacor, « Advantages of Hierarchical Organisation in Neural Networks », CASYS, 16 | 2004, 48-60.
Electronic reference
Yagmur Denizhan and Gursel Karacor, « Advantages of Hierarchical Organisation in Neural Networks », CASYS [Online], 16 | 2004, Online since 01 August 2024, connection on 27 December 2024. URL : http://popups.uliege.be/3041-539x/index.php?id=2330
Authors
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