[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/sci/ - Science & Math

Search:


View post   

>> No.9735686 [View]
File: 358 KB, 1920x1200, L2L1.png [View same] [iqdb] [saucenao] [google]
9735686

I have been reading this so many times but I just do not get what is different about L1 and L2 regularization.

How can summing absolute values of weights give a different result from summing squares of weights? The absolute values are all positive, so weights can not just cancel out and be set to zero, the same applies to squares.

Navigation
View posts[+24][+48][+96]