Model Selection, Underfitting and Overfitting

in the net.initialize(), we did not use parameter initializer package which means we would use the default, it is init.Uniform(scale=0.07), on the other hand we asssume the distribution of data is Gaussian, but why we not use init.Normal() to initialize the parameter? correct me if I am wrong, is there any reason or am I missing something important about the distribution of the data. Thank you.


You are right about it.

Check here:
We can use init.Normal() to initialize the parameter
check my answer…