$1.$ a$)$ Write a complete MATLAB program for creating and training Multilayer neural network that contains $3$ hidden layers for classifying four patterns $($P$1,$ P$2,$ P$3,$ P$4),$ such that:

$-$ Each pattern is described in $6$ binary pixels.

$-($black pixel is $0),($white pixel is $1)$

$-$ Patterns, P$1$ and P$2,$ belong to a class, called A$,$

$-$ Patterns, P$3$ and P$4,$ belong to another dass, called B$.$

the number of neurons in the first hidden layer is $2.$

the number of neurons in the second hidcen layer is $4,$

the number of neurons in the third hidden layer is $6,$

the error threshold is $0\mathrm{.}05$

the learning rate is $\backslash (0\mathrm{.}4^\{\backslash$text $\{*\}\}\backslash )(30$ Puan$)$

$2$

$1.$b$)$ How many input units that are used in the Mult layer neural network for solving the above problem? $*$

$6$ input units are used.

$1.$c$)$ How many output units that are used in the Multilayer neural network for solving the above problem? $*$