When training a neural network, the general process could be something like this:
While error < min_error
- Forward pass
- Compute error and cost funcion
- Back propagation
- Update weights
But when we get out of the loop because the error is small enaugh, if we save the neural network as it is, we are saving something that we have not tested yet. Wouldn't it be better to keep the previous weight values, as those are the ones for which we know the error?