1 / 22

Redes RBF no MATLAB 6.1

Redes RBF no MATLAB 6.1. Aproximação de uma Função. Função módulo de seno unitário, f = 1 Hz. Definição dos Padrões de Entrada. 10 neurônios: t10 = 0:0.1:0.9; 50 neurônios: t50 = 0:0.02:0.98;. Definição dos Padrões de Saída. y10 = abs(sin(2*pi*t10)); y50 = abs(sin(2*pi*t50));.

xexilia
Télécharger la présentation

Redes RBF no MATLAB 6.1

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Redes RBF no MATLAB 6.1

  2. Aproximação de uma Função • Função módulo de seno unitário, f = 1 Hz

  3. Definição dos Padrões de Entrada • 10 neurônios: t10 = 0:0.1:0.9; • 50 neurônios: t50 = 0:0.02:0.98;

  4. Definição dos Padrões de Saída • y10 = abs(sin(2*pi*t10)); • y50 = abs(sin(2*pi*t50));

  5. Definição dos Padrões de Teste • t10t = 0:0.001:0.9; • t50t = 0:0.0002:0.98;

  6. Definição dos Resultados Esperados • y10t = abs(sin(2*pi*t10t)); • y50t = abs(sin(2*pi*t50t));

  7. Importação dos Dados p/ NNTool

  8. Importação dos Dados p/ NNTool

  9. Definição das Redes • Network name: network1 • Tipo: Radial basis (exact fit) • Input data: Set to input (t10) • Target data: Set to target (y10) • Spread Constant: 0.01

  10. Definição das Redes • Network name: network2 • Tipo: Radial basis (exact fit) • Input data: Set to input (t10) • Target data: Set to target (y10) • Spread Constant: 1.0

  11. Definição das Redes • Network name: network3 • Tipo: Radial basis (exact fit) • Input data: Set to input (t10) • Target data: Set to target (y10) • Spread Constant: 100.0

  12. Definição das Redes • Network name: network4 • Tipo: Radial basis (exact fit) • Input data: Set to input (t50) • Target data: Set to target (y50) • Spread Constant: 0.01

  13. Definição das Redes • Network name: network5 • Tipo: Radial basis (exact fit) • Input data: Set to input (t50) • Target data: Set to target (y50) • Spread Constant: 1.0

  14. Definição das Redes • Network name: network6 • Tipo: Radial basis (exact fit) • Input data: Set to input (t50) • Target data: Set to target (y50) • Spread Constant: 100.0

  15. Testando as Redes RBF

  16. Testando as Redes RBF

  17. Exportando os Dados

  18. Exportando os Dados

  19. Visualizando os Resultados Redes com 10 neurônios >> figure >> plot(t10t, y10t, ’k’) >> hold on >> plot(t10t, s1, ’r’) >> plot(t10t, s2, ’b’) >> plot(t10t, s3, ’m’)

  20. Visualizando os Resultados Redes com 50 neurônios >> figure >> plot(t50t, y50t, ’k’) >> hold on >> plot(t50t, s4, ’r’) >> plot(t50t, s5, ’b’) >> plot(t50t, s6, ’m’)

  21. Implementação em m-file

  22. Otimização da largura das funções

More Related