## mean squared error (why mean?)

Hi
I found this equation in a machine learning book:
"we want to minimize the mean squared error:"
$E= \frac{1}{2} \sum_{n=1}^N (y-t)^2$

what I do not understand is the \frac{1}{2} , if it is a mean it should be \frac{1}{N},
why are they restricting to 2? In the text there is no reference to y or t being only 2. So it cannot be that N=2.
 Blog Entries: 8 Recognitions: Gold Member Science Advisor Staff Emeritus If you ask a question here, please always be sure to include the necessary reference. What book did you read this in? Title, author, page number?

Recognitions:
 Quote by sunone Hi I found this equation in a machine learning book: "we want to minimize the mean squared error:" $E= \frac{1}{2} \sum_{n=1}^N (y-t)^2$ what I do not understand is the \frac{1}{2} , if it is a mean it should be \frac{1}{N}, why are they restricting to 2? In the text there is no reference to y or t being only 2. So it cannot be that N=2.