0
$\begingroup$

What are the best educational sources for learning about transformers, what is the go to literature for a mathematician who considers themself a beginner in the subject?

Books, lecture notes, research papers, videos, etc.

Assume we are familiar with the material from: Machine Learning: A probabilistic perspective by Kevin Murphy

$\endgroup$
3
  • 1
    $\begingroup$ highly depends on your preparation and previous experience $\endgroup$
    – Alberto
    Apr 2 at 17:07
  • $\begingroup$ @Alberto say I am a mathematician with a good grasp of the material in Machine Learning: A probabilistic perspective by Kevin Murphy and Pattern Recognition and Machine Learning by Bishop. $\endgroup$
    – Monty
    Apr 2 at 17:21
  • $\begingroup$ then it depends on the usage you want to make about them, but a good paper on the topic for people that knows math is this one in my opinion arxiv.org/abs/2008.02217 (nothing to gain from a performance POV, but a better understanding of the attention module and why it might be so effective)... and I would say that is pretty much a book given the length $\endgroup$
    – Alberto
    Apr 2 at 17:31

1 Answer 1

0
$\begingroup$

For me personally, this was the book, which helped me really a lot. Read it and from time to time search on youtube "transformers from scratch".

$\endgroup$

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .