1
$\begingroup$

section 1.4.3 of the book "Machine Learning - A Probabilistic Perspective" gives an example about KNN:

the input is two dimensional, we have three classes, and K = 10

enter image description here

enter image description here

enter image description here

which contains a computation

$e_{10}{(0.1)} = 0.8$

what does that mean? what is the name of this computation?

Improve this question
$\endgroup$
3
  • 2
    $\begingroup$ $0.1^{1/10} = 0.79432823472428150206591828283639$, because $e_{D}(f) = f^{1/D}$ $\endgroup$
    – user158565
    Commented Jul 27, 2019 at 22:44
  • 1
    $\begingroup$ @user158565 thanks man! plz mv your comments to answer, I'll accept it $\endgroup$
    – czlsws
    Commented Jul 27, 2019 at 22:54
  • 1
    $\begingroup$ Too short. Cannot be Answer. $\endgroup$
    – user158565
    Commented Jul 27, 2019 at 22:56

1 Answer 1

Reset to default
2
$\begingroup$

This section uses this formula to compute

the expected edge length of this cube

$e_{D}(f) = f^{1/D}$

where, D = 10, so the original formula is $f^{1/10}$

and we want to base our estimate on 10%

which means f = 10% = 0.1

put above together

$e_{D}(f) = f^{1/D} = 0.1^{1/10} = 0.79 \approx 0.8$

using "= 0.8" other than "$\approx 0.8$" in OP may confused you.

Improve this answer
$\endgroup$

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.