Convolutional ensembles for Arabic Handwritten Character and Digit Recognition

A learning algorithm is proposed for the task of Arabic Handwritten Character and Digit recognition. The architecture consists on an ensemble of different Convolutional Neural Networks. The proposed training algorithm uses a combination of adaptive gradient descent on the first epochs and regular st...

Descripción completa

Detalles Bibliográficos
Autor principal: Palatnik de Sousa, Iam
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2018
Materias:
Algorithms and Analysis of Algorithms
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924465/
https://www.ncbi.nlm.nih.gov/pubmed/33816820
http://dx.doi.org/10.7717/peerj-cs.167

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924465/
https://www.ncbi.nlm.nih.gov/pubmed/33816820
http://dx.doi.org/10.7717/peerj-cs.167

Ejemplares similares