1. (a) Give a definition of learning in terms of tasks, experience, and performance measures. Give an example, making sure to identify the task, the experience, and the performance measure.[6 marks] (b) Describe the K-Nearest Neighbours algorithm for classification. (c) You are given the following training set:

The problem is to predict the label of each object in the following test set: (1,0), (0,0). i. Is this a regression or classification problem? ii. Solve this problem using the K-Nearest Neighbours algorithm with Euclide an distance and K = 3.[6 marks] (d) What is the computational complexity of the K-Nearest Neighbours algorithm? Explain briefly why. In your answer, you may assume that K is a fixed constant.[5 marks] (e) How would you summarize the difference between inductive and transductive algorithms in machine learning? Which of these two classes does K-Nearest Neighbours belong to?[5 marks] (f) Give two advantages and two disadvantages of the K-Nearest Neighbours algorithm.[8 marks]

Fig: 1

Fig: 2

Fig: 3

Fig: 4

Fig: 5

Fig: 6

Fig: 7

Fig: 8

Fig: 9

Fig: 10

Fig: 11

Fig: 12