Computational Intelligence - Problems for Chapter 11 -- Solution to part (c)

Go backward to Solution to part(b)
Go up to 1 Decision-tree Learning

Solution to part (c)

Explain how the learning bias inherent in learning decision-trees can be used to classify unseen instances. Give an instance that is not in the training data, show how the above tree classifies that instance. Justify why this is an appropriate classification.

From the 5 assignments of values to a, b and c in the training set, out of the 8 possible assignments, the decision tree makes predictions in all 8 cases. The ability to make predictions in unseen cases is the bias of the learning algorithm. The unseen cases are:

a b c prediction for d

true true true false

true false true false

false false false false

The bias is that c is always irrelevant to the classification, and that when a is true, b is also irrelevant. This is because c always seemed to be irrelevant in the training example. Similarly b was irrelevant when a was true.

a	b	c	prediction for d
true	true	true	false
true	false	true	false
false	false	false	false