R code: Train and evaluate the code from MNIST dataset(0,1,3,5).
a. Train 2 models, report the training and test accuracies.
b. Repeat a 10 times, i.e. you should obtain 10 train and test accuracies for each set.Calculate the average train and test accuracies over the 10 runs, and report them.
c. For 0,1 and 3,5 cases, explain if you observe any difference you in accuracy. Also, explain why do you think this difference might be.
d. This assignment deals with binary classification. Explain what you would do if you had more than two classes to classify, using logistic regression.