1
$\begingroup$

In the paper Large-Margin Softmax Loss for Convolutional Neural Networks the author has a figure as below: enter image description here

He is claiming that he is using only 2d features to classify MNIST with a CNN. How is he doing that? Is he reducing the dimension of MNIST images to 2 and how? How do you visualize such figures in 2D if the classification is for 10 classes?

$\endgroup$
0
$\begingroup$

I think I got my answer from the following post: http://unixnme.blogspot.com/2018/04/dimensionality-reduction-and-scattered.html

|improve this answer|||||
$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.