Write a matlab code for handwritten digit recognition using multilayer perceptron. The following files are provided:

$1.$ dzip.mat and azip.mat: the first is a vector that holds the digits $($the number$)$ and the second is an array of dimension $256$ x $1707$ that holds the training images. The images are vectors of dimension $256,$ which have been constructed from $16$ x $16$ images.

$2.$ dtest.mat and testzip.mat hold the test data.

$3.$ ima$2.$m takes an image vector as input and displays it$.$

ima$2.$m is the following

function $[]=$ima$2($A$)$

$\%$ Translate vector to become nonnegative

$\%$ Scale to interval $[0,20]$

$\%$ Reshape the vector as a matrix and then show image

a$1=$squeeze$($A$)$;

a$1=$reshape$($a$1,16,16)\text{'}$;

a$1=($a$1-$min$($min$($a$1))*$ones$($size$($a$1)))$;

a$1=(20/$max$($max$($a$1)))*$a$1$;

mymap$1=[1\mathrm{.}00001\mathrm{.}00001\mathrm{.}0000$

$0\mathrm{.}87150\mathrm{.}90280\mathrm{.}9028$

$0\mathrm{.}74310\mathrm{.}80560\mathrm{.}8056$

$0\mathrm{.}61460\mathrm{.}70830\mathrm{.}7083$

$0\mathrm{.}48610\mathrm{.}61110\mathrm{.}6111$

$0\mathrm{.}38890\mathrm{.}47220\mathrm{.}5139$

$0\mathrm{.}29170\mathrm{.}33330\mathrm{.}4167$

$0\mathrm{.}19440\mathrm{.}19440\mathrm{.}3194$

$0\mathrm{.}09720\mathrm{.}09720\mathrm{.}1806$

$000\mathrm{.}0417]$;

colormap$($mymap$1)$

image$($a$1)$