Sense of ResNet

[someone555777]

I watched few times video Why ResNets Work? And I still can’t understand sense of what we do

So, we pass output of layer additionally to computation to some of next layers. And? What is it at all? Ok, I listened, that it can be usefull, when weight decay is using, because intermidiary layers can only be skipped when w is near to zero.

So, all of this we need only for regularization? Or what?

[gent.spah]

Question about residual blocks and skipped connections

I understand that the purpose of the residual block is to mitigate a vanishing gradient, with the output of the residual block: a[l+2] = g ( W[l+2] . a[l+1] + b[l+2] + a[l] ) Firstly, in the case that the gradient goes to zero, does this not only affect dW, db? So rather than W, b → 0 would they not instead just remain constant? Surely for W, b → 0, this would have to have been learned and therefore suggest optimality? Secondly, why do we need the skipped connection? If instead we had: a…