Processing math: 100%

 

 

 

Compact expressions

We can define the inputs to the activation functions for the various layers in terms of various matrix-vector multiplications and vector additions. The inputs to the first hidden layer are

[z(1)1z(1)2]=([w(1)11w(1)12w(1)21w(1)22])T[a(0)1a(0)2]+[b(1)1b(1)2],

with outputs

[a(1)1a(1)2]=[σ(1)(z(1)1)σ(1)(z(1)2)].