New answers tagged

0 votes

Biometrics identification with embeddings comparison and "unknown"/"other" class/label

Learning an embedding and using k-Nearest Neighbor is one way to create a classification system. Another option would be to choose other classification algorithms, such as random forest. If a ...
user avatar
1 vote

Understand the reason of embedding and the size inside it in Pytorch

To answer your question. First think of only one column. Let's say your column has 10 unique values, so 10 categories. So, cat_szs will be 10. Then ...
user avatar
0 votes

Generalize min-max scaling to vectors

There are many different methods, none of which are going to be the best option all the time. Some maybe you could throw away based on some extra information you didn't provide ... but the real answer ...
user avatar

Top 50 recent answers are included