Subject Description Form

Subject Description Form

Subject Code COMP406
Subject Title Artificial Intelligence
Credit Value 3
Level 4
Pre-requisite COMP305
Objectives • To introduce the fundamental concepts of artificial intelligence;
• To equip students with the knowledge and skills in logic

programming using Prolog;
• To explore the different paradigms in knowledge representation and

reasoning;
• To understand the contemporary techniques in machine learning;
• To evaluate the effectiveness of hybridization of different artificial

intelligence techniques.
Intended Learning Upon completion of the subject, students will be able to:
Outcomes
Professional/academic knowledge and skills
a. understand the history, development and various applications of
artificial intelligence;
b. familiarize with propositional and predicate logic and their roles in
logic programming;
c. understand the programming language Prolog and write programs
in declarative programming style;
d. learn the knowledge representation and reasoning techniques in
rule-based systems, case-based systems, and model-based systems;
e. appreciate how uncertainty is being tackled in the knowledge
representation and reasoning process, in particular, techniques
based on probability theory and possibility theory (fuzzy logic);
f. master the skills and techniques in machine learning, such as
decision tree induction, artificial neural networks, and genetic
algorithm;
g. apply and integrate various artificial intelligence techniques in
intelligent system development as well as understand the
importance of maintaining intelligent systems.
Attributes for all-roundedness

h. explore the nature of human intelligence and its role in problem
solving;
i. deepen thoughts and understanding of human abilities such as
Last update in July 2014
learning, reasoning and planning;
j. appreciate the rooted philosophical arguments in logic and its
impact on human thoughts.
Subject Synopsis/
1. Artificial Intelligence (AI): its roots and scope
Indicative Syllabus
Early history and applications; the development of formal logic; the
Turing test; overview of AI application areas: game playing, automated
theorem proving, expert systems, natural language understanding and
semantics, planning and robotics, and machine learning.
2. Artificial intelligence as representation and search

The Propositional Calculus and Predicate Calculus; using inference rules
to produce predicate calculus expressions; strategies and structures for
state space search; heuristic search; recursion-based search; admissibility,
monotonicity and informedness of search algorithms.
3. Knowledge representation and reasoning

Rule-based production systems; case-based reasoning systems and model
based reasoning systems; reasoning under uncertain situations: stochastic
methods, fuzzy logic and fuzzy set theory; fuzzy expert systems.
4. Machine learning
Decision tree induction algorithms; artificial neural networks; genetic
algorithms.
5. Hybrid intelligent techniques and maintenance of intelligent

systems
Hybridization of neural networks, fuzzy logic, genetic algorithms and
other intelligent techniques for problem solving; maintenance of the
completeness, correctness and consistency of intelligent systems.
Teaching/Learning
Lectures
Methodology
During the lectures, students will come across the concepts, algorithms
and applications in artificial intelligence, and will be supplemented by
exercises, homework and project in machine learning. During the labs /
tutorials, students will have the opportunity to practice, apply, and use
PROLOG, Matlab toolboxes on fuzzy logics and neural networks.
Decision trees development and hybrid systems will also be introduced.

Assessment Methods
in Alignment with Specific % Intended subject learning outcomes to be
Intended Learning assessment weighting assessed (Please tick as appropriate)
Outcomes methods/tasks
a b c d e f g h i j
1. Assignments 15%
2. Project 25%
3. mid-term 15%
4. Exam 45%
Total 100 %
Student Study Class contact:

Effort Expected
Lectures 39 Hrs.
Tutorials/Lab 0Hrs.
Other student study effort:
Coursework and project 80 Hrs.
Total student study effort 119 Hrs.

1. George F. Luger, Artificial Intelligence: Structures and Strategies
Reading List and
for Complex Problem Solving, 6th Edition, Addison Wesley,
References
2009.
2. Sankar K. Pal and Simon C. K. Shiu, Foundations of Soft Case-
Based Reasoning, John Wiley, 2004.
3. Michael Negnevitsky, Artificial Intelligence: A Guide to
Intelligent Systems. 2nd edition, Addison Wesley, 2005.

Uploaded by

Uploaded by

Subject Description Form

Subject Code COMP406

Subject Title Artificial Intelligence

Objectives • To introduce the fundamental concepts of artificial intelligence;

• To equip students with the knowledge and skills in logic

• To explore the different paradigms in knowledge representation and

• To understand the contemporary techniques in machine learning;

• To evaluate the effectiveness of hybridization of different artificial

Attributes for all-roundedness

2. Artificial intelligence as representation and search

3. Knowledge representation and reasoning

5. Hybrid intelligent techniques and maintenance of intelligent

Last update in July 2014

Student Study Class contact:

Other student study effort:

Coursework and project 80 Hrs.

Total student study effort 119 Hrs.

Last update in July 2014

You might also like