2
$\begingroup$

What does it mean when in a machine learning paper there is $(arg)^{T}$, what does the T does to an arg 3b1b in this 3b1b video on neural networks he puts the: $(w^{l-1})^{T}$

$\endgroup$
3
  • $\begingroup$ In what context is this? could you provide the paper so we can see it ourselves? Or even better - quote it. Anyhow, raising to $T$ could be the transpose matrix when in context of linear algebra maths, but it also could just be a regular number and raising some other number to its power. Or, it could be something the authors of the paper defined themselves $\endgroup$
    – nir shahar
    Commented Apr 3, 2021 at 22:44
  • 2
    $\begingroup$ Yeah most likely transpose of a vector or matrix. $\endgroup$
    – awillia91
    Commented Apr 4, 2021 at 0:17
  • 1
    $\begingroup$ Please edit your question to provide more context. $\endgroup$
    – D.W.
    Commented Apr 4, 2021 at 1:42

1 Answer 1

4
$\begingroup$

The notation $A^T$ stands for the transpose of a matrix. It is not specific to machine learning, but rather standard notation in linear algebra. Other notations are sometimes used, for example $A'$.

A related operation is the adjoint $A^*$. The transpose and adjoint are equal for real matrices.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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