Affiliation:
1. FST, USMBA, Fes, Morocco
2. EST, UMI, Fes, Morocco
Abstract
Multilayer perceptron has a large amount of classifications and regression applications in many fields: pattern recognition, voice, and classification problems. But the architecture choice in particular, the activation function type used for each neuron has a great impact on the convergence and performance. In the present article, the authors introduce a new approach to optimize the selection of network architecture, weights, and activation functions. To solve the obtained model the authors use a genetic algorithm and train the network with a back-propagation method. The numerical results show the effectiveness of the approach shown in this article, and the advantages of the new model compared to the existing previous model in the literature.
Subject
Information Systems and Management,Management Science and Operations Research,Strategy and Management,Information Systems,Management Information Systems
Reference16 articles.
1. A new model selection strategy in artificial neural networks
2. Neural architectures optimization and Genetic algorithms.;M.Ettaouil;WSEAS Transactions on Computers,2009
3. Architecture optimization model for the multilayer perceptron and clustering.;M.Ettaouil;Journal of Theoretical & Applied Information Technology,2013
4. Architecture Optimization and Training for the Multilayer Perceptron using Ant System.;Y.Ghanou;International Journal of Computational Science,2016
5. Comparison of new activation functions in neural network for forecasting financial time series
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献