Mostrar el registro sencillo del ítem
Multilayer Perceptron: Architecture Optimization and Training
| dc.contributor.author | Ramchoun, Hassan | |
| dc.contributor.author | Ghanou, Youssef | |
| dc.contributor.author | Ettaouil, Mohamed | |
| dc.contributor.author | Janati Idrissi, Mohammed Amine | |
| dc.date | 2016-09 | |
| dc.date.accessioned | 2021-07-07T10:37:59Z | |
| dc.date.available | 2021-07-07T10:37:59Z | |
| dc.identifier.issn | 1989-1660 | |
| dc.identifier.uri | https://reunir.unir.net/handle/123456789/11569 | |
| dc.description.abstract | The multilayer perceptron has a large wide of classification and regression applications in many fields: pattern recognition, voice and classification problems. But the architecture choice has a great impact on the convergence of these networks. In the present paper we introduce a new approach to optimize the network architecture, for solving the obtained model we use the genetic algorithm and we train the network with a back-propagation algorithm. The numerical results assess the effectiveness of the theoretical results shown in this paper, and the advantages of the new modeling compared to the previous model in the literature. | es_ES |
| dc.language.iso | eng | es_ES |
| dc.publisher | International Journal of Interactive Multimedia and Artificial Intelligence (IJIMAI) | es_ES |
| dc.relation.ispartofseries | ;vol. 4, nº 1 | |
| dc.relation.uri | https://ijimai.org/journal/bibcite/reference/2523 | es_ES |
| dc.rights | openAccess | es_ES |
| dc.subject | genetic algorithms | es_ES |
| dc.subject | optimization | es_ES |
| dc.subject | architecture | es_ES |
| dc.subject | nonlinear operation | es_ES |
| dc.subject | multilayer perceptron | es_ES |
| dc.subject | IJIMAI | es_ES |
| dc.title | Multilayer Perceptron: Architecture Optimization and Training | es_ES |
| dc.type | article | es_ES |
| reunir.tag | ~IJIMAI | es_ES |
| dc.identifier.doi | http://doi.org/10.9781/ijimai.2016.415 |
