Train more a Neural Network to have more consistent results every time?
3 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Jean-François
el 11 de Nov. de 2015
Respondida: Greg Heath
el 11 de Nov. de 2015
Hello
Before using Matlab, i was programming my own Neural Networks, and when i trained them long enough, i had the same simulation outputs everytime (approximatively).
Now i use Matlab and on my predictions, i don't always have the same consistent results.
So do i need to train the NN longer?
And how do i do that properly?
thanks!!
Jeff
0 comentarios
Respuesta aceptada
Greg Heath
el 11 de Nov. de 2015
Results are different because the initial state of the RNG is different. Therefore you will get different random data divisions and initial weights.
For nontrivial problems this often results in a wide variety of results.
It is not unusual for me to designs 100 nets in a double for loop:
1. Initialize the RNG
2. Outer loop over 10 trial values for number of hidden nodes:
h = Hmin:dH:Hmax
3. Inner loop over Ntrials = 10 different initial RNG states.
i = 1:Ntrials.
I have posted zillions of examples in both the NEWSGROUP and ANSWERS. Search using "greg" with the above code snippets.
Hope this helps.
Thank you for accepting my answer
Greg
0 comentarios
Más respuestas (0)
Ver también
Categorías
Más información sobre Sequence and Numeric Feature Data Workflows 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!