|
Abstract
|
|
|---|---|
| In this paper we present the Newton neural network. We state several theorems that reveal this trained net as the best approximator to any curve or surface with the least number of training patterns. The low number of training samples is an advantage in this type of neural networks, as it affects substantially lowering the computational cost and training time. AMS Subject Classification: 68T05 Key Words: backpropagation, artificial neural networks, adaptive learning, functional-link neural networks | |
|
International
|
Si |
|
JCR
|
Si |
|
Title
|
International Journal of Pure and Applied Mathematics |
|
ISBN
|
1311-8080 |
|
Impact factor JCR
|
|
|
Impact info
|
|
|
Volume
|
82 |
|
|
http://dx.doi.org/10.12732/ijpam.v82i4.13 |
|
Journal number
|
4 |
|
From page
|
639 |
|
To page
|
661 |
|
Month
|
SIN MES |
|
Ranking
|
|