Unsupervised-Classification-with-Autoencoder icon indicating copy to clipboard operation
Unsupervised-Classification-with-Autoencoder copied to clipboard

Published 20 hours ago • verified publisher icon ardamavi
→

Metadata

Using Autoencoders for classification as unsupervised machine learning algorithms with Deep Learning.

Results 1 Unsupervised-Classification-with-Autoencoder issues
Sort by recently updated
recently updated
newest added

Why should the classification function be designed like this?

Hello ardamavi, I find that two classification functions in "MNIST" and "DOG_CAT" are different. The function in "MNIST" is x+x*K.one_hot, whereas the function in "DOG_CAT" is x-x+K.one_hot. So I wonder...

takagi97 avatar takagi97

← Metadata

47
Stars
16
Forks
Watchers

Owner

verified publisher icon ardamavi

Metadata

Using Autoencoders for classification as unsupervised machine learning algorithms with Deep Learning.

Back