Por favor, use este identificador para citar o enlazar este ítem: http://dspace.utpl.edu.ec/jspui/handle/123456789/18706
Título : Learning Algorithm for the Recursive Pattern Recognition Model
Autor : Aguilar Castro, J.
Palabras clave : Engineering controlled terms: Character recognition
Pattern recognition Engineering main heading: Learning algorithms
metadata.dc.date.available: 2017-06-16T22:02:14Z
Fecha de publicación : 8-ago-2016
Editorial : Applied Artificial Intelligence
Resumen : In this work, we incorporate a learning algorithm to the recursive pattern recognition model, based on the systematic functioning of the human neocortex presented in previous works. This algorithm has two mechanisms: the first, called Aprendizaje_nuevo, is used to learn new patterns and creates a new pattern recognition module in the model. The other, called Aprendizaje_por_refuerzo, is used to reinforce a pattern and adapts the module that represents the pattern to the changes in it. The algorithm is tested in various contexts (text and images) to analyze its capacities of learning and of recognition of the model. © 2016 Taylor & Francis.
metadata.dc.identifier.other: 10.1080/08839514.2016.1213584
URI : http://dspace.utpl.edu.ec/handle/123456789/18706
ISBN : 8839514
Otros identificadores : 10.1080/08839514.2016.1213584
Otros identificadores : 10.1080/08839514.2016.1213584
metadata.dc.language: Inglés
metadata.dc.type: Article
Aparece en las colecciones: Artículos de revistas Científicas

Ficheros en este ítem:


Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.