How to handle non-numeric? about cnn-from-scratch HOT 3 CLOSED

You need to add the "Unknown" class in the output layer and also need to mix the class relevant data with the MNIST set while training.

from cnn-from-scratch.

so, it would not be possible to add "Unknown" class without adding data during training?

It looks like that the NN is eagerly want to answer even though the answer does not exist.

from cnn-from-scratch.

Q: so, it would not be possible to add "Unknown" class without adding data during training?
A: Standard? No!
Naively? yes. By thresholding on the output scores (logits) before the softmax probabilities layer. There is always some naive way.

Q: It looks like that the NN is eagerly want to answer even though the answer does not exist.
A: It is just a demonstration for digits. We can always engineer around that to build what we want.

from cnn-from-scratch.