Welcome to the InfoSci Platform
Reference Hub1
Multilayer Perceptron New Method for Selecting the Architecture Based on the Choice of Different Activation Functions

Multilayer Perceptron New Method for Selecting the Architecture Based on the Choice of Different Activation Functions

Hassan Ramchoun, Mohammed Amine Janati Idrissi, Youssef Ghanou, Mohamed Ettaouil
Copyright: © 2019 |Volume: 11 |Issue: 4 |Pages: 14
ISSN: 1935-5688|EISSN: 1935-5696|EISBN13: 9781522564737|DOI: 10.4018/IJISSS.2019100102
Cite Article Cite Article

MLA

Ramchoun, Hassan, et al. "Multilayer Perceptron New Method for Selecting the Architecture Based on the Choice of Different Activation Functions." IJISSS vol.11, no.4 2019: pp.21-34. http://doi.org/10.4018/IJISSS.2019100102

APA

Ramchoun, H., Idrissi, M. A., Ghanou, Y., & Ettaouil, M. (2019). Multilayer Perceptron New Method for Selecting the Architecture Based on the Choice of Different Activation Functions. International Journal of Information Systems in the Service Sector (IJISSS), 11(4), 21-34. http://doi.org/10.4018/IJISSS.2019100102

Chicago

Ramchoun, Hassan, et al. "Multilayer Perceptron New Method for Selecting the Architecture Based on the Choice of Different Activation Functions," International Journal of Information Systems in the Service Sector (IJISSS) 11, no.4: 21-34. http://doi.org/10.4018/IJISSS.2019100102

Export Reference

Mendeley
Favorite Full-Issue Download

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.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.