A practical way to view neural networks (whiteboard view)

 A whiteboard view:



You can take a decision matrix view of ReLU neural networks.

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

Popular posts from this blog

Neon Bulb Oscillators

23 Circuits you can Build in an Hour - Free Book

Q Multiplier Circuits