A practical way to view neural networks (whiteboard view)
A whiteboard view:
Instead of ReLU(Wx) you create a diagonal matrix with binary 1 or 0 entries according to the ReLU decisions (x>=0?)
Then conceptually a layer is DWx. Where D is doing row selection on W.
And in fact D does column selection on the weight matrix in the next layer.
That is very coarse parameter selection which is linear mapping selection.

Comments
Post a Comment