1
$\begingroup$

There is mse function: C = $\frac{1}{2n}$ * $\sum(length(y - a)^2)$

why not just use C = $\sum(length(y - a))$ ?

(where "length" is the vector's length, "y" - ideal network's output, "a" - current network output)

$\endgroup$
1
$\begingroup$

You're talking about L1 norm and L2 norm. Both work for neural networks. However, they are different:

Without more information, I can't comment on how L2 norm is better (or worse) for your problem.

$\endgroup$
  • $\begingroup$ but this problem is solved by length function, is not it? $\endgroup$ – Dmitry Nalyvaiko Mar 9 '17 at 10:01
  • $\begingroup$ @DmitryNalyvaiko What do you mean by length? $length(a - b) = |a - b|$? $\endgroup$ – Łukasz Grad Mar 9 '17 at 10:03
  • $\begingroup$ @ŁukaszGrad y - a = some_vector. we take the length of the some_vector to: 1) make result scalar, 2) make difference absolute $\endgroup$ – Dmitry Nalyvaiko Mar 9 '17 at 10:04
-1
$\begingroup$

Short answer: both can be used.

Longer answer: both measures are in active use. The first measure is based on the Euclidean distance, the second one on the taxi-cab distance. Or more formally: the $L_2$ distance and the $L_1$ distance.
Which is better depends on the context. Intuitively: the Euclidean distance prefers many small/medium errors over a few big errors while the taxi-cab distance is more forgiving when it comes to a few large errors. Which one is preferable depends on the context and what you are trying to achieve.

$\endgroup$
  • $\begingroup$ you are talking about length function, but I'm asking why result of length function should be powerd by 2? $\endgroup$ – Dmitry Nalyvaiko Mar 9 '17 at 11:59
  • $\begingroup$ That could be because you want to 'punish' big errors in certain training cases over the same error spread over multiple training cases. Suppose over 2 training cases one algorithm has an error of 0 and 3 respectively and another algorithm has an error of 2 for both training cases. Squaring the errors would make the second algorithm preferable, not squaring would have the first algorithm as better. The right choice depends on the context $\endgroup$ – dimpol Mar 9 '17 at 12:12
  • $\begingroup$ > Squaring the errors would make the second algorithm preferable 0^2 + 3^2 = 9; 2^2 + 2^2 = 8; why second algorithm is preferable? $\endgroup$ – Dmitry Nalyvaiko Mar 9 '17 at 13:43
  • $\begingroup$ An error-score of 8 is lower than an error-score of 9, lower error-score is preferable. $\endgroup$ – dimpol Mar 10 '17 at 22:20

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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