0

Having a dataset for which 3 different outcomes exist, but there might be missing values for these outcomes, can neural networks training in lasagne deal with this NAN or should a neural network be trained for each outcome (where NAN cases are removed from training)?

Lets say we have the following targets:

1,2,3
NAN,1,5
1,NAN,2
0,NAN,NAN

Please note that imputation is not what I am interest in.

SwatchPuppy
  • 324
  • 1
  • 3
  • 15
  • your nan inputs will be propagated to all your results. – Feras Oct 29 '16 at 22:27
  • No, you cannot calculate a gradient with nans. Just multiply the cost function with 0 wherever you don't have information, so the gradient will be 0 and won't get backpropagated. – Chrigi Nov 07 '16 at 14:54

0 Answers0