We will define a class to model the fully connected multi layer network. The network parameters will be a dictionary accesssed with keys $"$W$1","$b$1","$W$2","$b$2",$ etc.

The weight matrix is initialized with random values from a normal distribution with variance $1.$ For example, to create a matrix $w$ of dimension $34,$ with values

from a normal distribution with variance $1,$ we write $w=0\mathrm{.}01**torch.$ randn $,$ requires$\_$grad$=$True, dtype$=$torch.float $32$