This programming assignment is to simulate $3-$layer neural network with a backpropagation algorithm

to classify the following non$-$linear separable problem. You can use your favorite computer language.

Do not use Machine learning libraries for this question.

The training labelled data are given below.

Train your $3-$layer neural network to classify this problem. For this assignment, the architecture is

given as $2$ input units, $3$ hidden units, and $2$ output units.

Since the activation function is a sigmoid function, the actual output cannot be exactly either one or

zero like the target output. In programming, when the actual output of the output unit is larger than

$0\mathrm{.}9,$ we accept the output as $1.$ When the actual output of the output unit is less than $0\mathrm{.}1,$ we accept the

output as $0.$

You will start with your small random initial weights for this problem. You should try different

learning coefficients to run your program.

As the result of training, your program should print vour weighted sum and actual output

$($produced from Sigmoid function$)$ for each input $(00,01,10,11)$ to verify your actual output is close

enough to target output. Your program also should print the final connections weights as the result of

training.