An effective way to generate neural network structures for function approximation.

Bastian, Andreas. "An effective way to generate neural network structures for function approximation.." Mathware and Soft Computing 1.2 (1994): 139-161. <http://eudml.org/doc/39023>.

@article{Bastian1994,
abstract = {One still open question in the area of research of multi-layer feedforward neural networks is concerning the number of neurons in its hidden layer(s). Especially in real life applications, this problem is often solved by heuristic methods. In this work an effective way to dynamically determine the number of hidden units in a three-layer feedforward neural network for function approximation is proposed.},
author = {Bastian, Andreas},
journal = {Mathware and Soft Computing},
keywords = {Redes neuronales; Teoría del aprendizaje; Algoritmos polinomiales},
language = {eng},
number = {2},
pages = {139-161},
title = {An effective way to generate neural network structures for function approximation.},
url = {http://eudml.org/doc/39023},
volume = {1},
year = {1994},
}

TY - JOUR
AU - Bastian, Andreas
TI - An effective way to generate neural network structures for function approximation.
JO - Mathware and Soft Computing
PY - 1994
VL - 1
IS - 2
SP - 139
EP - 161
AB - One still open question in the area of research of multi-layer feedforward neural networks is concerning the number of neurons in its hidden layer(s). Especially in real life applications, this problem is often solved by heuristic methods. In this work an effective way to dynamically determine the number of hidden units in a three-layer feedforward neural network for function approximation is proposed.
LA - eng
KW - Redes neuronales; Teoría del aprendizaje; Algoritmos polinomiales
UR - http://eudml.org/doc/39023
ER -