Adaptive Pointing Theory (APT) Artificial Neural Network
Data(s) |
01/05/2014
|
---|---|
Resumo |
The choice value and the testing process against the vigilance parameter, characteristic of ART Neural Network, are merged. Only, a single unique test is required to determine if a committed category node can represent the current input or not. Advantages of APT over ART are: 1-Avoid testing every committed category node before deciding to train a committed category node or a new node must be committed, 2-The vigilance parameter is fixed during training, and 3-The choice value parameter is eliminated. |
Formato |
application/pdf |
Identificador | |
Idioma(s) |
spa |
Publicador |
E.T.S. de Ingenieros Informáticos (UPM) |
Relação |
http://oa.upm.es/35627/1/35627_INVE_MEM_2014.pdf http://www.ijcce.org/ info:eu-repo/semantics/altIdentifier/doi/10.7763/IJCCE.2014.V3.322 |
Direitos |
http://creativecommons.org/licenses/by-nc-nd/3.0/es/ info:eu-repo/semantics/openAccess |
Fonte |
International Journal of Computer and Communication Engineering, ISSN 2010-3743, 2014-05, Vol. 3, No. 3 |
Palavras-Chave | #Química |
Tipo |
info:eu-repo/semantics/article Artículo PeerReviewed |