could you help giving me explanation on this problem ? Thank you

Consider the following L2-regularized 2-layer neural network training problem: w:= argminw=[w(),w(2] eNN(w; A) := [elys, y(xs;W)) +1(IW 217 + (W2)IF) , (5) S= 1 where 1 2 0 is a L2-regularization constant. This will penalize the weight matrices W, W2) to have large L2-norm. Derive the gradient of the above loss function