HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Neural Network Topology Optimization

Mohammed Attik 1 Laurent Bougrain 1 Frédéric Alexandre 1
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : The determination of the optimal architecture of a supervised neural network is an important and a difficult task. The classical neural network topology optimization methods select weight(s) or unit(s) from the architecture in order to give a high performance of a learning algorithm. However, all existing topology optimization methods do not guarantee to obtain the optimal solution. In this work, we propose a hybrid approach which combines variable selection method and classical optimization method in order to improve optimization topology solution. The proposed approach suggests to identify the relevant subset of variables which gives a good classification performance in the first step and then to apply a classical topology optimization method to eliminate unnecessary hidden units or weights. A comparison of our approach to classical techniques for architecture optimization is given.
Complete list of metadata

Contributor : Mohammed Attik Connect in order to contact the contributor
Submitted on : Thursday, November 10, 2005 - 9:55:35 AM
Last modification on : Friday, February 4, 2022 - 3:18:02 AM




Mohammed Attik, Laurent Bougrain, Frédéric Alexandre. Neural Network Topology Optimization. 15th International conference on Artificial Neural Networks - ICANN 2005, Sep 2005, Warsaw/Poland, pp.53--58, ⟨10.1007/11550907⟩. ⟨inria-00000623⟩



Record views