Prev Up
Go backward to Solution to Question 1, part 2
Go up to Question 1

Solution to Question 1, part 1

Is there a tree that correctly classifies the training examples, but represents a different function than those found by the preceding algorithms? If so, give it. If not, explain why.

There are 4 missing cases for which there are no examples. Thus there are 24=16 different Boolean functions that classify the examples correctly, of which we have found two! There are 14 other such trees.

Here is one such tree:

if(author = known, 
       if(length = long, skips, reads), 
       if(where_read = work, 
          if(thread = follow_up, skips, reads),
          skips))). 
which predicts an example with author=unknown, thread=new, length=short, where_read=home will have classification skips, where the other trees classifies this as reads.
Prev Up