The nearest neighbour classifier Suppose we have a data set D consisting of records with numeric attributes and a binary class attribute (e.g., TRUE or FALSE). Now suppose we obtain a new data point p (whose class is unknown to us) and we want to use the 1-NN and 3-NN algorithms to predict p's class based on the classes of its neighbours in D. Assume Manhattan distance as the distance metric for both 1-NN and 3-NN. Explain which of the following is correct:

a) If 1-NN classifies p as TRUE using D, then 3-NN must also classify p as TRUE using D b) If 3-NN classifies p as TRUE using D, then 1-NN must also classify p as TRUE using D c) Both a) and b) are true d) Neither a) nor b) is true