Replace softmax

[makremGRIFT]

Hi everybody,
I'm testing this example (LeNet5) as shown in this tuto, with some changes it work very well. then I remove the softmax layer, and apply gaussian distribution to the output. For each iteration, I call net:forward(input), calculate the gaussian of all values in output and continue with criterion and backward. After some iterations, output becomes a nan vector.
Can anyone explain this behaviour ?
Thanks in advance