UNIVERSITI KUALA LUMPUR SAMPLE COURSE: BEB45104

UniKL BMI
COURSE LEARNING PLAN
To be shared with students.

SECTION A: COURSE DETAILS

1 Course Name Artificial Intelligence
2 Course Code BEB45104
3 Academic Dr. Aizat Faiz Ramli, PhD (Univ. York)
Staff Name(s)
4 Rationale for Artificial Intelligence is commonly used in smart and intelligent system found at home
inclusion of (home appliances) and in the industry. Student should understand the theory and
Course in the principles of Artificial Intelligence, and able to develop Artificial Intelligence systems
Programme based on fuzzy logic and neural network.
5 Semester & Semester: 6/7
Year Offered Year: ¾
6 Student
Learning Face to Face (F2F) Independent
TOTAL
Time (SLT) learning
Lecture Tutorial Practical Other TOTAL
34 10 24 2 70 90 160
7 Credit Value 4 credits
8 Prerequisite None
9 Learning Upon completion of this course, students should be able to :
Outcomes 1. Be able to Cooperate with team members and Discuss the application of
artificial intelligence techniques to solve real world problems. (A5)
2. Analyse the implementations of Artificial Intelligence techniques and is able
to use the concept to Design a system. (C6)
3. Apply and Investigate the practical implementations of Artificial Intelligent
techniques to solve real world problems. (P5)

10 Transferable Skills Development of the skills Skills assessment

skills 1. Teamwork Students are required to work in Teacher’s observation
teams during assignments and evaluation – rubric

2. Participation & Students are required to present Teacher’s evaluation –

Communication findings in written and oral forms presentation (rubric)
Skill

11 Strategies
Teaching & learning Assessment

 Lecture  PBL (Problem Based Learning)

 Group Discussion  Assignment 1
 Practice Tutorial  Assignment 2
 simulation  Final Exam
 Self study
12 Synopsis This unit comprises the basic concept of Fuzzy logic fundamentals and Neural
networks. This includes the fuzzy set theory, many valued logic, rule based approaches
in artificial intelligence, approximate reasoning, possibility theory, the basic concepts
of fuzzy control, modeling of fuzzy systems, an introduction to the basic models of
neural computing, perceptrons, and back propagation networks. In short it emphasizes

COURSE LEARNING PLAN | Page 1 of 6

UNIVERSITI KUALA LUMPUR SAMPLE COURSE: BEB45104

the area of computational intelligence or soft computing. The delivery will include
lectures, group discussions, assignments and case studies.

13 Mode of Lecture, tutorial, practical and discussion

Delivery
PBL 10%
Assignment 1 20%
Assignment 2 30%
Final examination 40%
TOTAL 100%
15 Mapping of PEO 1 PEO 2 PEO 3 PEO 4 PEO 5
Course to
Programme
Educational
✓
Objectives
(PEOs) (✓)
16 Mapping of
Course to
Programme
Learning PLOs ()
Outcomes CLOs
01 02 03 04 05 06 07 08 09 10 11 12
(PLOs)
1 
2 
3 

17 References Main Additional

1. Michael Negnevitsky, Artificial 1. Lefteri H.Tsoukalas & Robert E.
Intelligence, A guide to Uhrig,Fuzzy and Neural Approaches in
Intelligent System, Addison Engineering, Wiley Interscience, 2000
Wesley 3rd Edition 2011
2. Russell, S. J. & Norvig, P.
(2015). Artificial Intelligence: A
Modern Approach. Pearson
Education.
18 Additional
information
(if any)

COURSE LEARNING PLAN | Page 2 of 6

UNIVERSITI KUALA LUMPUR SAMPLE COURSE: BEB45104

UniKL BMI
COURSE LEARNING PLAN
To be shared with students.

SECTION B: LEARNING SCHEDULE

Delivery Relevant
When Topic
Method Assessments
1.0 Intelligent machines  Lecture  Exam
WEEK 1

 Discussion
1.1 Intelligence, thinking, artificial intelligence

Outcome(s): CLO 1,CLO 2

2.0 Fuzzy systems  Lecture  PBL
 
dates are
optional)

Discussion Exam
WEEK 2

(Exact

2.1 What is fuzzy system?

2.2 Fuzzy sets, Linguistic variables and hedges

Outcome(s): CLO 1, CLO 2

2.0 Fuzzy systems  Lecture  PBL
 Practical  Exam
WEEK 3

2.1 Operation of fuzzy sets

2.2 Fuzzy rules

Outcome(s): CLO 1, CLO 2

2.0 Fuzzy systems  Lecture  Assignment 1
 Practical  PBL
WEEK 4

2.1 Fuzzy inference: Mamdani, Sugeno  Exam

2.2 Building fuzzy expert system: fuzzification,
fuzzy-inference, defuzzification

Outcome(s): CLO 1 ,CLO 2, CLO 3

2.0 Fuzzy case studies  Lecture  Assignment 1
WEEK 5

 Practical  PBL
2.1 Using Fuzzy to solve problems  Exam

Outcome(s): CLO 2, CLO 3

2.0 Fuzzy simulation  Lecture  Assignment 1
WEEK 6

 Practical
2.1 Simulation of case studies

Outcome(s): CLO 3
2.0 Fuzzy simulation  Lecture  Assignment 1
WEEK 7

 Discussion
2.1 Simulation of case studies

Outcome(s): CLO 3
3.0 Artificial Neural Networks (ANN)  Lecture  Exam
 Discussion
WEEK 8

3.1 Introduction to ANN.

3.2 Machine learning, neural network, modelling the
brain, learning, adjusting weight

Outcome(s): CLO 2, CLO 3

COURSE LEARNING PLAN | Page 3 of 6

UNIVERSITI KUALA LUMPUR SAMPLE COURSE: BEB45104

3.0 Artificial Neural Networks (ANN)  Lecture  Assignment 2

 Practical  Exam
WEEK 9
3.1 Neuron as simple computing element
3.2 Determining output, activation function

Outcome(s): CLO 2, CLO 3

3.0 Artificial Neural Networks (ANN)  Lecture  Assignment 2
 
WEEK 10

Practical Exam
3.1 Supervised Single layer ANN:
 The perceptron

Outcome(s): CLO 2, CLO 3

3.0 Artificial Neural Networks (ANN)  Lecture  Assignment 2
 
WEEK 11

Practical Exam
3.2 Supervised Single layer ANN:
 The perceptron

Outcome(s): CLO 2, CLO 3

3.0 Artificial Neural Networks (ANN)  Lecture  Assignment 2
 
WEEK 12

Practical Exam
3.1 Supervised Multilayer ANN: Multi layer
Perceptron (MLP)

Outcome(s): CLO 2, CLO 3

3.0 Artificial Neural Networks (ANN)  Lecture  Assignment 2
WEEK 13

 Discussion  Exam
3.1 Backpropagation algorithm in MLP

Outcome(s): CLO 2, CLO 3

3.0 Artificial Neural Networks (ANN)  Lecture  Assignment 2
 
WEEK 14

Discussion Exam
3.1 Learning Issues in MLP
3.2 Validation and testing schemes

Outcome(s): CLO 2, CLO 3

3.0 Artificial Neural Networks (ANN)  Lecture  Assignment 2
 
WEEK 15

Practical Exam
3.1 Accelerated Learning in Multilayer ANN

Outcome(s): CLO 2, CLO 3

3.0 Artificial Neural Networks (ANN)  Lecture  Assignment 2
 Practical  Exam
WEEK 16

3.1 Hebbian Learning

Outcome(s): CLO 2, CLO 3

3.0 Artificial Neural Networks (ANN)  Lecture  Assignment 2
WEEK 17

 Practical  Exam
3.1 Self-Orgnising Map

Outcome(s): CLO 2, CLO 3

WEEK 18

REVISION WEEK

COURSE LEARNING PLAN | Page 4 of 6

UNIVERSITI KUALA LUMPUR SAMPLE COURSE: BEB45104

WEEK 19
EXAMINATION WEEK
WEEK 20

EXAMINATION WEEK

TOTAL Student Learning Time (hours) 160

COURSE LEARNING PLAN | Page 5 of 6

UNIVERSITI KUALA LUMPUR SAMPLE COURSE: BEB45104

UniKL BMI
COURSE LEARNING PLAN

SECTION C: COURSE LEARNING PLAN APPROVAL

Course Name Artificial Intelligence

Course Code BEB45104

Subject Matter Expert & Expert Work Group Signature Date

1 Dr. Aizat Faiz Ramli

Approved by

Head of Section
(Signature, Date & Stamp)

COURSE LEARNING PLAN | Page 6 of 6