Write your own Performance criteria in Neural Network?

Is it possible to write your own stopping criteria in a Neural Network? How should this be done?
I want to use the Mean Squared Error method, but on data not known by the Network.
e.g I use the following divideFcn, so every data will be training data
net.divideFcn = 'dividenull'; %Only training data
(or 'dividetrain' in more recent versions of matlab)
How can I add my personal stopping criteria on an other data set?

 Respuesta aceptada

Greg Heath
Greg Heath el 2 de Abr. de 2012
See my expression for MSEgoal in
Additional details can be found by searching for MSEgoal in both the Newsgroup and Answers.
Hope this helps.
Greg

Más respuestas (0)

Categorías

Más información sobre Deep Learning Toolbox en Centro de ayuda y File Exchange.

Preguntada:

el 1 de Abr. de 2012

Community Treasure Hunt

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

Start Hunting!

Translated by