NPTEL Introduction to Machine Learning Week 6 Assignment Answers 2024 (July-October)

Week 6: Assignment 6 Solutions for Machine Learning Course

Description:
Find all the answers and explanations for Week 6: Assignment 6 of the "Introduction to Machine Learning" course. This article will provide a detailed breakdown of each question, along with the correct answers and the reasoning behind them. Ideal for students looking to understand the concepts better and prepare for their assignments.

---

Question 1: Entropy for a 90-10 split between two classes is:

• a) 0.469
• b) 0.165
• c) 0.204
• d) None of the above

Answer: a) 0.469

Reason:
Entropy is a measure of impurity or disorder in a set. For a 90-10 split, the entropy is calculated using the formula:
$\text{Entropy} = -p \log_2(p) - (1-p) \log_2(1-p)$
Where $p = 0.9$ and $1-p = 0.1$. Plugging in these values gives an entropy of approximately 0.469.

---

Question 2: Consider a dataset with only one attribute (categorical). Suppose there are 8 unordered values in this attribute, how many possible combinations are needed to find the best split point for building the decision tree classifier?

• a) 511
• b) 120
• c) 512
• d) 127

Answer: c) 512

Reason:
For a categorical attribute with 8 unordered values, each value can either be on the left or right side of the split. This leads to $2^8$ combinations, minus the case where all values are on one side, resulting in 512 combinations.

---

Question 3: Having built a decision tree, we are using reduced error pruning to reduce the size of the tree. We select a node to collapse. For this particular node with 8 branches, there are remaining data points with the following outputs: 5, 7, 9, 6, and 8 for the left branch. The other remaining data points along the branches of 3, 6, 5, 11, and 7. What are the values for response_left, response_right?

• a) 6, 9
• b) 7, 8, 10, 11, 6
• c) 5, 8, 9
• d) None of the above

Answer: Explanation needed to solve this.