Get premium membership and access revision papers, questions with answers as well as video lessons.
Foundation Of Learning And Adaptive Systems Question Paper
Foundation Of Learning And Adaptive Systems
Course:Bachelor Of Science In Information Technology
Institution: Kca University question papers
Exam Year:2009
UNIVERSITY EXAMINATIONS: 2008/2009
THIRD YEAR EXAMINATION FOR THE DEGREE OF BACHELOR OF
SCIENCE IN INFORMATION TECHNOLOGY
BIT 3103: FOUNDATION OF LEARNING AND ADAPTIVE SYSTEMS
DATE: AUGUST 2009 TIME: 2 HOURS
INSTRUCTIONS: Answer question ONE and any other TWO questions
QUESTION ONE
(a) Define following terms (4 Marks)
i) Training data set:
ii) Rational Agent
iii) Artificial Immune systems
(b) Von Neumann programming paradigm borrows from Von Neumann architecture. Show sequence
of steps in Von Neumann machine architecture or discuss working of Von Neumann machine
(3Marks)
(c) A 4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the learning rate
being equal to 2. The inputs are 4, 10, 5 and 20 respectively. Compute the output of the network.
(4 Marks)
(d) What do the following terms applied in adaptive systems mean? (6 Marks)
i) Iteration:
ii) Sub optimal
iii) Self Organising:
2
(e) According to psychologists, the Tabula rasa view - contends that babies are a ‘blank tablet .. on
which the record of experience is gradually impressed ’. Explain how this understanding can aid in
machine learning (2 Marks)
(f) Give arguments in favour of parallel computing/programming (2 Marks)
(g) Give a structure of parallel programming recipe. (2 Marks)
(h) What is your understanding of a Belief Network as used in Bayesian Learning? (4 Marks)
(i) Show the role of Unification and Backtracking in logic programming (3 Marks)
QUESTION TWO
Consider the following six training examples, where each example has three attributes: color, shape
and size. Color has three possible values: red, green and blue. Shape has two possible values: square
and round. Size has two possible values: big and small. (20 Marks)
Example Color Shape Size Class
1 Red square big +
2 Blue square big +
3 Red round small -
4 green square small -
5 Red round big +
6 green square big -
• Determine the best attribute for the root node of decision tree.
QUESTION THREE
(a) Discuss Artificial neural networks explaining where it gets inspiration from (4 Marks)
(b) Compare a learning algorithm like Artificial Neural Network (ANN) and conventional
programming (5 Marks)
3
(c) Write the pseudocode to represent the backpropagation algorithm in artificial neural networks
(6 Marks)
(d) What programming language would you use to represent the above algorithm? Explain
(5 Marks)
QUESTION FOUR
a) Discuss your understanding of “adaptive systems” (5 Marks)
b) Why is it necessary for research in machine learning? Give one reason (2 Marks)
c) List THREE(3) applications of adaptive systems (3 Marks)
d) Using an example, discuss one area where Adaptive Systems can or are used. (10Marks)
QUESTION FIVE
A learning theory may be divided into the following parts:
(1) A hypothesis space;
(2) A representation for hypotheses
(3) A preference criterion over hypotheses, independent of the data
(4) A measure of how well a given hypothesis fits given data.
(5) A search strategy to find a good hypothesis for a given data set.
For the machine learning method of your choice, explain what each of these is (20 Marks)
More Question Papers
Popular Exams
Return to Question Papers