Idrissi, M.A.J. and Ramchoun, H. and Ghanou, Y. and Ettaouil, M. (2016) Genetic algorithm for neural network architecture optimization. In: UNSPECIFIED.

Full text not available from this repository.
Official URL:


The optimization of architecture of feed-forward neural networks is a complex task of high importance in supervised learning because it has a great impact on the convergence of learning methods. In this paper, we propose a multi-objective mathematical formulation in order to determine the optimal number of hidden layers, the number of neurons in each layer and good values of weights. We will solve our mathematical modeling using a hybridation of the famous genetic algorithm and the back-prop training algorithm. For evaluating our approach, we apply it to benchmark classification problems data-iris, seed, and wine. The obtained results demonstrated the effectiveness of the proposed approach. © 2016 IEEE.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: Complex networks; Genetic algorithms; Multiobjective optimization; Neural networks; Optimization, Benchmark classification; Hidden layers; Learning methods; Mathematical formulation; Multi objective; Optimal number; Supervised trainings; Training algorithms, Network architecture
Subjects: Business, Management and Accounting
Divisions: SCIENTIFIC PRODUCTION > Business, Management and Accounting
Depositing User: Administrateur Eprints Administrateur Eprints
Last Modified: 31 Jan 2020 15:44

Actions (login required)

View Item View Item