-1
$\begingroup$

Hi I'm an undergraduate student interested in Machine Learning. I was reading a paper from ICLR 2020 and came a cross a weird looking vector dimensions.

Can anyone tell me what this means??

$\mathbb{R}^{768\times (768 * 2)}$

Does this mean that in python numpy array the shape would probably be (2, 768, 768) ?? I remember reading that the numpy array dimensions are reversed from the actual vector dimensions representations. And the vector I asked about shows up in page 4.

$\endgroup$
2
  • $\begingroup$ I meant to ask the meaning of 768 x (768 * 2). $\endgroup$
    – Aesop
    Jun 27, 2020 at 14:34
  • $\begingroup$ Can you link to the article? $\endgroup$
    – noe
    Jun 28, 2020 at 8:01

2 Answers 2

3
$\begingroup$

To my knowledge, that notation refers to a matrix which is of shape 768 by 1536. I am guessing the 2 is there to highlight that the dimension increase is proportional to the 768 (whether that is the input shape to a layer in a neural network, for example).

$\endgroup$
0
$\begingroup$

$\mathbb{R}^{m\times n}$ refers to the real-valued matrices of dimension $m$ by $n$.

$\mathbb{R}$ refers to real values (-$\infty$ to +$\infty$).

See here for an example, https://en.wikipedia.org/wiki/Matrix_(mathematics)#Notation

$\endgroup$

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.