Question $1(35$ pts$)$: Answer the following questions:

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

Each pattern is described in $6$ binary pixels.

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

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

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

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

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

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

the error threshold is $0\mathrm{.}06$

the learning rate is $0\mathrm{.}4$

Solution: $($use the keyboard$)$

b$)$ How many input units that are used in the Multilayer neural network for solving this problem?

Solution: $($use the keyboard$)$

c$)$ How many output units that are used in the Multilayer neural network for solving this problem?

Solution: $($use the keyboard$)$

Please write the code clearly.