Document

UNIVERSITY OF GHANA
(All Rights Reserved)

FIRST SEMESTER 2017/2018 EXAMINATIONS
DEPARTMENT OF COMPUTER ENGINEERING
LEVEL 400: CPEN 405: ARTIFICIAL INTELLIGENCE
3 CREDIT HOURS
TIME ALLOWED: 3 Hours
II INSTRUCTION: Attempt All Questions II

Ql. (a) Explain the different approaches used in defining artificial intelligence? [4 marks]
(b) How far is AI from reaching human-level intelligence? When will it
happen? Support your answer with facts and figures from modern technological
advancements. [4 marks]
(c) Describe briefly the Turing Test for artificial intelligence systems. [4 marks]
(d) If The Turing Test is passed does this show that computers exhibit intelligence?
State your reasons. [4 marks]
(e) What advances do you think need to be made in order for The Turing Test to be
passed? [4 marks]
Q2. (a) Consider the 8-puzzle problem described in the textbook and homework
assignments. We would like to search for a solution using A* - search. Describe the
following aspects of the problem formulation: a) states, b) successor function,
c) goal test, d) step cost, and e) path cost. [8 marks]
(b) For A*-search the evaluation function, J(n), consists of the path cost, g(n), plus the
heuristic function, h(n). 'We will use the Manhattan distance between the current
state and the goal state to be the heuristic function. Explain when a heuristic
function is admissible and prove this fact for the Manhattan distance heuristic.
[5 marks]
(c) Describe when a heuristic is consistent and proof this for the lVlanhattan distance
heuristic. [2 marks]
(d) For each of the following activities, give a PEAS description of the task environment
and characterize it in terms of observability, number of agents, randomness,
dynamism and continuity.
i. Playing soccer. [5 marks]
ii. Ta.xi driving agent [5 marks]
Exnrniner-: RobeTt A. So'Wah (PhD) Page 1 of 4

Q3. Suppose you have the following search space:
State Next Cost

A B 4
A C 1
B D 3
B E 8
C C 0
C D 2
C F 6
D C 2
D E 4
E G 2
F G 8
(a) Draw the state space of this problem. [2 marks]
(b) Assume that the initial state is A and the goal state is G. Show how each of the
following search strategies would create a search tree to find a path from the initial
state to the goal sLate:
i. Uniform cost search [4 marks]
ii. Iterative deepening search [4 marks]
At each step of the search algorithm, show which node is being expanded, and the
content of fringe. Find the eventual solution found by each algorithrn, and the
solution cost.
Q4. (a) Name and describe the main features of Genetic Algorithms (GA). [10 marks]
(b) State the main difference betwwen Genetic algorithms and Simulated annealing
methods of optimization. [5 marks]
(c) Assume we have the following test function for genetic algorithm optimization
f(x) = x" - 603;2 + 900x + 100

where x is constrained to lie between 0 :<::: x :<::: 31. 'Ne wish to ma.ximize I(x).
Using a binary representation we call represent :c using five binary digits.
l. Prove frOln first principles using Calculus that the optintal value is :r; = JO.
Find the corresponding I(:c) value. [6 marks]

ii. Given the following four chromosomes, give the values for x and I(x)
Chromosome Binary String

PI 11100
P2 01111
P3 10111
P4 00100
Examiner: Robert A. SOUJah (PhD) Page 2 of 4

a) If P3 and P2 are chosen as parents and we apply one point crossover show
the resulting children, Cl and C2. Use a crossover point of 1 (where 0 is
to the very left of the chromosome) [5 marks]
(3) Do the same using P4 and P2 with a crossover point of 2 and create C3
and C4 [5 marks]
I) Calculate the value of x and f(x) for Cl, C2, C3, and C4. [8 marks]
Q5. (a) What is Machine Learning? Give five (5) application areas. [7 marks]
(b) \~hat is difference between supervised and unsupervised learning algorithms? Give
an example each of both supervised and unsupervised learning algorithms [4 marks]
(c) A tennis player came on a vacation. For a fortnight, she played tennis given the
following weather conditions as given in Table 1 below.
Day Outlook Temperature Humidity Wind PlayTennis
01 Sunny Hot High Weak No
02 Sunny Hot High Strong No
03 Overcast Hot High Weak Yes
04 Rain Mild High Weak Yes
05 Rain Cool Normal Weak Yes
06 Rain Cool Normal Strong No
07 Overcast Cool Nannal Strong Yes
08 Sunny Mild High Weak No
09 Sunny Cool Normal Weak Yes
OlD Rain lvlild Nonnal Weak Yes
011 Sunny Mild Normal Strong Yes
012 Overcast Mild High Strong Yes
013 Overcast Hot Normal Weak Yes
014 Rain Mild High Strong No
I. Use the Iterative Oichotomiser 3 (103) algorithm to build a decision tree from
the given tennis dataset. You should build a tree to predict PlayTennis, based
on the other attributes (except the Day attribute). Show all of your work,
calculations, and decisions as you build the tree. [25 marks]
ii. On the eve of 015 the weather forecast showed was [Outlook: Rain,
Temperature: Hot, Humidity: High, Wind: Weak]. Predict whether the athlete
will play tennis on that day. [4 marks]
Ill. What is the classification accuracy'! [3 marks]
ExamineT: RobeTl A. Sowah (PhD) Page 3 of 4

Q6. (a) Consider the following Bayesian network as given in ligure 1, where F
having the flu and C = coughing:
P(C I F) =0.8
P(F) =0.1 P(C I --, F) =0.3
Figure 1: Bayesian network
1. Write dOWll the juint prolm\.Jility table specified by the BaYI::sian llet\v(Jrk.[~ nlarksj
(b) We have a bag of three biased coins a, b, and c with probabilities of coming up
heads of 20%, 60%, and 80%, respectively. One coin is drawn randomly from the
bag (with equal likelihood of drawing each of the three coins), and then the coin is
flipped three tinles to generate thl~ OutCOlll€S XI, X 2 ) and .IYJ .
I. Draw the Bayesian network corresponding to this setup and deline the necessary
CPTs.
[5 marks]
11. Calculate which coin was most likely to have been drawn from the bag if the
observed flips come out heads twice and tails once.

[5 marks]
(c) In your local nuclear power station, there is an alarm that senses when a tern perature
gauge exceeds a given threshold. The gauge measures the temperature of the core.
Consider the Boolean variables A (alarm sounds), FA (alarm is faull.y), a.nd Fc
(gauge is fauUy) and the multivalued nodes G (gauge reading) and T (act:ll.al COTe
tempemtuTe) .
i. Draw a Bayesian network for this dOlnain, given that the gauge is rnare likely
to fail when the core temperature gets too high.
[4 marks]
n. Suppose the alarm works correctly unless it is faulty, in which case it never
sounds. Give the conditional probability table associated with A.
[5 marks]
lll. Suppose the alarm and gauge are working and the alarm sounds. Calculate an
expression for the probability that the temperature of the core is too high, in
terms of the various conditional probabilities in the network.
[5 marks]
Examine,': Rober·t A. S07JJah (PhD) Page 4 of 4

Document

Uploaded by

Copyright:

Available Formats

Document

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Document

Uploaded by

Copyright:

Available Formats

UNIVERSITY OF GHANA

(All Rights Reserved)

II INSTRUCTION: Attempt All Questions II

Exnrniner-: RobeTt A. So'Wah (PhD) Page 1 of 4

State Next Cost

f(x) = x" - 603;2 + 900x + 100

Find the corresponding I(:c) value. [6 marks]

Chromosome Binary String

Examiner: Robert A. SOUJah (PhD) Page 2 of 4

ExamineT: RobeTl A. Sowah (PhD) Page 3 of 4

Figure 1: Bayesian network

observed flips come out heads twice and tails once.

Examine,': Rober·t A. S07JJah (PhD) Page 4 of 4

You might also like