A$.$ Build a baseline model $(5$ marks$)$

Use the Keras library to build a neural network with the following:

$-$ One hidden layer of $10$ nodes, and a ReLU activation function

$-$ Use the adam optimizer and the mean squared error as the loss function.

$1.$ Randomly split the data into a training and test sets by holding $30\%$ of the data for testing. You can use the train$\_$test$\_$split

helper function from Scikit$-$learn.

$2.$ Train the model on the training data using $50$ epochs.

$3.$ Evaluate the model on the test data and compute the mean squared error between the predicted concrete strength and the actual concrete strength. You can use the mean$\_$squared$\_$error function from Scikit$-$learn.

$4.$ Repeat steps $1-3,50$ times, i$.$e$.,$ create a list of $50$ mean squared errors.

$5.$ Report the mean and the standard deviation of the mean squared errors.

Submit your Jupyter Notebook with your code and comments.