Přístupnostní navigace
E-application
Search Search Close
Publication detail
Petr Šmíd
Original Title
Genetic Algorithm for Training Artificial Neural Networks With Backpropagation
Type
conference paper
Language
English
Original Abstract
The paper deals with training the neural models of microwave structures. The first, an artificial neural network (ANN) is trained with basic genetic algorithm (GA). Training abilities are discussed. Further, the modification of GA and an approach to learning artificial neural networks (ANN) with backpropagation is described. Neural networks are implemented in MATLAB. Results of training abilities are compared. Finally, some ideas for improving the training process are mentioned
Keywords
Artificial Neural Networks, Genetic Algorithm
Authors
RIV year
2005
Released
1. 4. 2005
Publisher
Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií a Fakulta informačních technologií
Pages from
637
Pages to
641
Pages count
5
BibTex
@inproceedings{BUT14763, author="Petr {Šmíd}", title="Genetic Algorithm for Training Artificial Neural Networks With Backpropagation", booktitle="STUDENT EEICT 2005 - Proceedings of the 11-th conference", year="2005", pages="5", publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií a Fakulta informačních technologií" }