0
$\begingroup$

I have 2 neural netowks and I am training them in different way. 1 neural network is generating good predictions and ending up with a certain loss. Another neural network is not doing good predictions. So I am trying to make the second neural network end up at the loss value of the first well performed neural network by adding bias to the gradient. Does ending up at the same loss guarantees that 2 neural networks are the same?

Improve this question
$\endgroup$
1
  • 2
    $\begingroup$ You should explain what you mean by "the same," but the answer is almost certainly going to be "no, the networks are not guaranteed to be the same." $\endgroup$
    – bogovicj
    Nov 27, 2022 at 14:12

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy