Hi. I have an unbalance problem on my dataset, I have three or four times more positive data than negative. I would like that my CNN, at training, penalizes hardly when a negative samples is classified incorrectly. I think that I should change the cost in order to do that, but I do not know how. If someone could give me some tricks I would be very pleased.
I am using the logistic regression cost implemented in the theano tutorial. Thank you very much in advance. Kind regards. Beatriz. -- --- You received this message because you are subscribed to the Google Groups "theano-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/d/optout.
