Detail výsledku

Neural Network Training using Genetic Algorithm

GAŽAR, R. Neural Network Training using Genetic Algorithm. Mendel 2004 10th Internacional Conference on Soft Computing. Brno: Faculty of Mechanical Engineering BUT, 2004. p. 161-166. ISBN: 80-214-2676-4.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Gažar Roman, Mgr., FIT (FIT)
Abstrakt

This paper deals with the aggregation of  two well known computing paradigm  - neural networks (NN) and genetic algorithms (GA). GA in NN area can be used for searching weight values, topology design, NN parameter settings and for selection and ordering of input and output vectors for training and testing set. We focused only on the weight  searching by GA. The structure of NN is fixed and it is not changed throw all experiments. The feed-forward NN is used with one hidden layer and standard sigmoidal transfer function. We used standard genetic algorithm with  external setting of its parameters

Klíčová slova

neural network, genetic algorithm, training set, weight selection

Rok
2004
Strany
161–166
Sborník
Mendel 2004 10th Internacional Conference on Soft Computing
Konference
Mendel 2004, 10th International Conference on Soft Computing
ISBN
80-214-2676-4
Vydavatel
Faculty of Mechanical Engineering BUT
Místo
Brno
BibTeX 
@inproceedings{BUT17339,
  author="Roman {Gažar}",
  title="Neural Network Training using Genetic Algorithm",
  booktitle="Mendel 2004 10th Internacional Conference on Soft Computing",
  year="2004",
  pages="161--166",
  publisher="Faculty of Mechanical Engineering BUT",
  address="Brno",
  isbn="80-214-2676-4"
}
Projekty
Predikce a ladění paralelní výkonnosti, GAČR, Standardní projekty, GA102/02/0503, zahájení: 2002-01-01, ukončení: 2004-12-31, ukončen
Pracoviště
Ústav počítačových systémů (UPSY)
Nahoru