1
$\begingroup$

I am trying to build a binary classifier using a MLP with the Keras package in R.

My question is, why does the package require the labels to be a one-hot vector? For example, the value 1 will be the vector [1,0] and the value 0 will be the vector [0,1]. This essentially makes the labels a 2D array.

$\endgroup$
1
  • $\begingroup$ You'll have to ask the people who made the software to explain their design choices; anything else is just guessing. $\endgroup$
    – Sycorax
    Commented Mar 1, 2021 at 18:41

0

Browse other questions tagged or ask your own question.