Is there any function that'll show the cost of the neural network on a training sample? Or perhaps do the training examples return the residue of the dataset? I ask this because i wish to make sure i'm not overfitting or underfitting with cross-validation. Thanks!
What about net.test method?
I see, that works. Thanks for the help!
Sign up for the SourceForge newsletter:
You seem to have CSS turned off.
Please don't fill out this field.