Imagine you have a network that is trying to predict a categorical response with three levels(categories) and uses a softmax activation function on the final layer. If there is just one node in the L-1 layer and that node has an activation value of 5 for a particular observation,

use the parameters given below to calculate the probability of the observation being in class 1.

The probability is:

0 : (W . = -0.2; W/- = 0.4; W/2 = 0.1, b- = 0.3, by = -0.2, b2 = 0.8