CS4811: Homework 6 --- Knowledge Representation
and Machine Learning
(Chapters 7 & 9)
Due: Friday, March 24, 2006, beginning of class. (Assigned: Friday, March 17, 2006.)
Reminder:
This is an individual assignment. All the work should be the
author's and in accordance with the university's academic integrity policies.
You are allowed to use any written source in preparing your
answers, but if you use any other source than the textbook and the class
notes, you should specify it on your assignment.
Question 1. (40 points)
For each of the following statements:
a) translate the sentence into conceptual dependency representation,
b) translate the sentence into a conceptual graph, and
c) translate the conceptual graph in part b to predicate
calculus.
If any of the translations is not possible, explain why. Show a partial
translation if you believe a full one is not possible.
1. John believes Jane likes flowers.
2. John gave Jane a flower.
3. Jane liked the flower.
4. Jane watered the flower.
Question 2: (30 points)
Consider the problem of defining a good home computer. For simplicity,
we will use 4 attributes:
- Memory capacity can be 1GB-or-less or more-than-1GB, i.e., the allowable
vaules are from { 1GB, 1GB+};
- The screen can be LCD or CRT, i.e., the allowable values are from
{lcd, crt};
- The CPU can be 1.8GHz, 2 GHz, or 3 GHz, i.e., the allowable values are
from {1.8, 2, 3};
- The mouse can be cordless or regular, i.e., the allowable values are
from {c, r}.
Consider the following examples in the given order:
- + (1GB lcd 2 c)
- - (1GB+ lcd 2 c)
- + (1GB crt 2 c)
- - (1GB lcd 1.8 c)
- + (1GB crt 2 r)
Initialize the G and S sets to {W, X, Y, Z} and { }, respectively, and
show their values after each example. Be sure to fully document why you
came up with a particular set.
Question 3: (30 points)
Consider the following training set. The objective is
to learn a decision tree that determines whether a particular alien will
appear in a movie.
| Example # |
Number of eyes |
Pointy forehead |
Webbed fingers |
Appears? |
| 1 |
1 |
Y |
N |
Y |
| 2 |
1 |
N |
N |
Y |
| 3 |
1 |
N |
N |
Y |
| 4 |
2 |
N |
N |
Y |
| 5 |
2 |
N |
N |
N |
| 6 |
3 |
N |
N |
N |
| 7 |
3 |
N |
N |
N |
| 8 |
3 |
N |
N |
N |
| 9 |
3 |
Y |
Y |
N |
Show the decision tree that would be generated by a decision tree learning
algorithm employing the "probability of error" heuristic? Show
all
your calculations.