How to overcome poor prediction of neural network.

1 visualización (últimos 30 días)
Nitin
Nitin el 23 de Abr. de 2014
Respondida: Greg Heath el 28 de Abr. de 2014
I have created a neural network with nftool for prediction with default settings. Data used for input is matrix of 19x1140 i.e 19 input parameter and 1x1140 i.e 1 output parameter. The regression values comes around .99 and .98 but during prediction using sim(net,test) command it gives wrong prediction. How to solve this problem?

Iniciar sesión para responder a esta pregunta.

Respuesta aceptada

Greg Heath
Greg Heath el 28 de Abr. de 2014
Use datadivision and as few hidden nodes as possible. Repeat multiple times to get a good set of random initial weights.
What do you mean by prediction ... the test set performance?

Más respuestas (0)

Categorías

Más información sobre Function Approximation and Clustering en Help Center y File Exchange.

Etiquetas

Productos

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by