With
f=1{font=serif} and
d=1{display=popup}, the
model-
matrix input is
The
feedforward neural network has three inputs,
a fully connected layer of two
ReLU units, and
a fully connected two-class
softmax output. Algebraically,
h=ReLU(Wx+b),z=Vh+c,pk=ez0+ez1ezk,
where
W∈R2×3,
b∈R2,
V∈R2×2, and
c∈R2. The coding is
0 for no click and
1 for
a click. There are
parameters.
New to topics? Read the docs here!