Specifying Neural Network output range to either 0 or1
2 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Hello
I have two questions
1. When I train my data with Neural Network, I want the answer to be either 0 or 1, because it means "Faulty/Non-faulty". I used "softmax" & "tansig" for output and hidden layer, Although the out put is really near 1 and 0 but they are not crisp. how can I get exact 1 and 0 output.
2. I tried to change the number of epochs, but whenever I run the program, it runs for 1000 iterations
Thanks In advance
Golnoosh
0 comentarios
Respuesta aceptada
Greg Heath
el 31 de Ag. de 2013
1. With only 2 classes you can replace softmax with logsig for training and use. Then either
a. Use round: help round, doc round
or
b. Replace logsig with hardlim: help hardlim, doc hardlim
2. net.trainParam.epochs = 100;
Hope this helps.
Thank you for formally accepting my answer
Greg
0 comentarios
Más respuestas (0)
Ver también
Categorías
Más información sobre Deep Learning Toolbox en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!