Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.
Sign up to join this community
In one-hot encoding, a vector is given to each class label. For each class, only one entry of the vector is equal to 1 and the remaining entries are zeros in this encoding.
Thus, in one-hot encoding, we are encoding the class label.
Is it true that label-embedding gives a vector for each class label like in one-hot encoding? Is one-hot encoding a type of label-embedding?
