my_multinom: Implement multinomial logistic regression
In kimgannon/bis557: Contains Homework Assignments for BIS 557 2020

This function implements multinomial logistic regression, generalizing to k classes

1	my_multinom(X, Y, lr, max_n, tol = 1e-10)

`X`	a model matrix, the X variables as columns
`Y`	a factor vector, the response variable
`lr`	the learning rate
`max_n`	max number of iterations (a positive integer)
`tol`	the difference threshold for which we will exit the algorithm for iterations less than max_n