R^2 for comparing the results of measured vs. predicted (non-linear model) values

I use the neural network toolbox for creating empirical relations between different parameters. The same relations are used to extrapolate the data for the remaining data set. Since the neural network is a highly non-linear framework, can I use R^2 as the statistic measure to compare the predicted values and the measured values?

Answer 1

[Greg Heath]

Yes. Search the NEWSGROUP and ANSWERS with

 greg and one of Rsq R2 R2a R2trn R2trna R2val R2tst

Hope this helps.

Thank you for formally accepting my answer

Greg

[Ashish]

Hi Greg, a formal link to it would be highly appreciated.

[Greg Heath]

In order to give you a formal link I would have to

Search the NEWSGROUP and ANSWERS with

 greg and one of Rsq R2 R2a R2trn R2trna R2val R2tst