Assignment Task: Machine Learning Question with hand computation and R programming based.
Question 1: Consider the following simple dataset, consisting of five mows and two columns:
|
Row nr.
|
column 1
|
column 2
|
|
1
|
0
|
3
|
|
2
|
1
|
3
|
|
3
|
1
|
2
|
|
4
|
3
|
1
|
|
5
|
4
|
2
|
We are interested in creating K = 2 clusters by applying Lloyd's algorithm. Suppose that the initial random assignment in step 1 of the algorithm yields the two clusters C1 = {1, 4} and C2 = {2, 3, 5}. Now work through the rest of the algorithm by hand (and hence show your working), and report the optimal set of clusters that the algorithm generates in this case.
Question 2: Your colleague at the insurance company has recently started learning about clustering. He has just completed his first attempt to apply Lloyd's algorithm for K-means clustering to a certain dataset and asks you to comment on his results. He shows you the following graph, which shows for K = 1, 2, . . . , 10 the optimal 'total within-cluster sum of squares' i.e. k=1∑KW(Ck) as computed by R's kmeans() function:
What irregularity do you observe in this graph, and what (small) change would you advise your colleague to make in his It code to try to resolve it? Briefly motivate your answer.
Tutorsglobe by means of its industry best professional tutors offer the top-notch Machine Learning Assignment Help service to all the students, who are in academic needs!
Tags: Machine Learning Assignment Help, Machine Learning Homework Help, Machine Learning Coursework, Machine Learning Solved Assignments