New Scaled Conjugate Gradient Algorithm for Training Artificial Neural Networks Based on Pure Conjugacy Condition

Conjugate gradient methods constitute excellent neural network training methods characterized by their simplicity efficiency and their very low memory requirements. In this paper, we propose a new scaled conjugate gradient neural network training algorithm which guarantees descent property with stan...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Khalil K. Abbo, Hind H. Mohamed
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	University of Kirkuk 2015-09-01
Edice:	Kirkuk Journal of Science
Témata:	feed forward neural networks training algorithms
On-line přístup:	https://kujss.uokirkuk.edu.iq/article_104992_de92aae565f76a728ed3fd8136233195.pdf
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!