Please use this identifier to cite or link to this item:
|Title:||How Many Hidden Layers and Nodes?|
|Citation:||INTERNATIONAL JOURNAL OF REMOTE SENSING vol. 30 no. 8 p. 2133-2147|
|Publisher:||TAYLOR & FRANCIS LTD|
|Type:||Articles in periodicals and books|
|Abstract:||The question of how many hidden layers and how many hidden nodes should there be always comes up in any classification task of remotely sensed data using neural networks. Until today there exists no exact solution. In this paper a method able to give an answer to this question is presented. Based on searching with a genetic algorithm a near-optimal solution is discovered. A novel fitness function is introduced that concurrently seeks for the most accurate and compact solution. The proposed method is thoroughly compared to many of the methods currently in use, including several heuristics and pruning algorithms. The results are encouraging, indicating that it is time to shift our focus from suboptimal practices to efficient search methods, in tuning the parameters of neural networks.|
|JRC Institute:||Institute for the Protection and Security of the Citizen|
Files in This Item:
There are no files associated with this item.
Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.