Assignment 10.

1.  Problem 1 was provided in class.

2. Generate decision trees to represent the following Boolean functions:

  1. A Ù Ø B
  2. A Ú [ B Ù C]
  3. A XOR B
  4. [ A Ù B ] Ú [ C Ù D]

3. Consider the following set of training examples:

Instance

Classification

attribute a1

attribute a2

1

+

T

T

2

+

T

T

3

-

T

F

4

+

F

F

5

-

F

T

6

-

F

T
  1. What is the entropy of this collection of training examples with respect to the target function classification?
  2. What is the information gain of attribute a2 relative to these training examples?