I didn’t understand this part at all. We had matrix Wya and how did we simplify it to Wy? And what is the difference between Wya and Wy at all?
W_{ya} refers to weights for multuplying an a like quantity to get a y like quantity.
W_y is for notational convenience, to convey to the reader the output quantity that’s computed (without showing the input quantity) i.e. y. It’s the same as W_{ya}
oh, ok, thx. So, Wy is just more short notation of Wya