COURSE OUTLINE

Department/ Software Engineering /Computing Page: 1 of 4

Faculty:
Course code: SCSJ 3553 Academic Session/Semester: 20202021/1

Course name: Artificial Intelligence Pre/co requisite (course name Data Structure
and code, if applicable):
Credit hours: 3

Course synopsis This course offers students a new perspective on the study of Artificial Intelligence (AI)
concepts. The essential topics and theory of AI are presented, but it also includes practical
information on data input and reduction as well as data output (i.e. algorithm usage). In
particular, this course emphasizes on theoretical and practical aspects of various search
algorithms, knowledge representations, and machine learning methods. The course features
practical implementations through assignments undertaken both individually and in groups.

Course coordinator Dr Aida Ali

Course lecturer(s) Name Office Tel (07-55) E-mail (@utm.my)

Dr Aida Ali N28-207-15 [email protected]

Mapping of the Course Learning Outcomes (CLO) to the Programme Learning Outcomes (PLO), Teaching & Learning (T&L)
methods and Assessment methods:

Weigh *Taxonomies T&L ***Assessment

PLO
No. CLO t (%) and methods methods
(ICGPA CODE)
**generic skills
Lecture,
Explain the basic definition
CLO1 PLO1 (KW) 40 C3 Active Q, M, F
and concept of AI.
learning,
Identify the types of AI
techniques and understand
Lecture,
the role of search
CLO2 PLO3(PS) 30 C3, A2 Active A, M, F
algorithms, knowledge
learning
representation, and
machine learning methods
Formulate appropriate
Lecture,
solutions for problems and C4, A3
CLO3 PLO3 (PS) 20 Active A, P, R, F
design intelligent computer-
learning
based systems
Develop team-working skills
for implementing AI C6, A5
CLO4 PLO8 (AD) 10 Project P, R
techniques in real-world AD3
problems.
*Taxonomies of Learning **UTM’s Graduate Attributes, where applicable for measurement of outcomes achievement
***M – Mid-term Test; Q – Quiz; A – Assignment; P –Project; R –Report; F – Final Exam
Details on Innovative T&L practices:
Prepared by: Certified by:
Name: Dr. Afnizanfaizal Abdullah Name: Assoc. Prof. Dr. Siti Zaiton Mohd Hashim
Signature: Signature:

Date: 23 August 2017 Date:

Department/ Software Engineering /Computing Page: 2 of 4
Faculty:
Course code: SCSJ 3553 Academic Session/Semester: 20182019/1

Course name: Artificial Intelligence Pre/co requisite (course name Data Structure
and code, if applicable):
Credit hours: 3

No. Type Implementation

1. Lecture Conducting face-to-face learning session
2. Active learning Conducting in-class activities
3. Project Analysing real-world case studies, elucidating problem, and proposing solutions

Weekly Schedule:
Computer and Intelligence
Week 1 - Introduction to thinking, computer architecture, and intelligence.
(18-22 Oct) - What is artificial intelligence (AI)? Strong AI vs Weak AI
- AI timeline and current trend
Knowledge Representation
- What is knowledge representation? (frame-based, semantic graph etc)
- Importance of representing knowledge
Week 2-3
- Syntax and semantics
(25 - 5 Nov)
- Propositional logic
Quiz1
- Predicate logic
- Inference process
- Proof procedure
Structure for Problem Solving
Week 4
- Graph theory
(8 – 12Nov)
- Structures for state space
Asg1
- Search strategies: data- and goal-driven
Project
- Implementation and evaluation
Search Algorithms
Week 5
- Exhaustive search algorithms
(15-19 Nov)
- Breadth-first search
Quiz2
- Depth-first search
Week 6-7 Search Algorithms (Continued)
(22 Nov -3 - Heuristic search algorithm
Dec) - Heuristic evaluation and best first search (including A* search)
Test1 18Oct - Evaluation criteria (admissibility, monotonicity, and informedness)
Week 8
MID SEMESTER BREAK
(6-10 Dec)
Week 9 Problem Solving with Search
(13-17 Dec) - Game playing (minimax and alpha-beta)
Asg2 - Search engine, social media and bots
Search Planning and Control
Week 10 - Recursion based search
(20-24 Dec) - Pattern based search
- Implementation in image processing and pattern recognition
Week 11-12 Advanced Artificial Intelligence
(27 Dec - 7 - Agent and distributed-based search
Jan) - Smart computing applications
Machine Learning
Week 13-14 - Overview of machine learning
(10-21 Jan) - Supervised vs unsupervised learning
Asg3 - Classification, clustering, and reinforcement
- Data Analytics
Week 15
Project Demo / Competition
(24-28 Jan)
Department/ Software Engineering /Computing Page: 3 of 4
Faculty:
Course code: SCSJ 3553 Academic Session/Semester: 20182019/1

Course name: Artificial Intelligence Pre/co requisite (course name Data Structure
and code, if applicable):
Credit hours: 3

Week
REVISION WEEK AND FINAL EXAM
16 - 18
Transferable skills (generic skills learned in course of study which can be useful and utilised in other settings):
Team working
Writing technical report

Student learning time (SLT) details:

Distribution
of student Teaching and Learning Activities TOTAL
Learning SLT
Time (SLT)
Course Guided Learning Guided Learning Independent Learning
content (Face to Face) Non-Face to Face Non-Face to face
outline
CLO L T P O
CLO 1 20h 18h 38h
CLO 2 5h 5h 16h 26h
CLO 3 5h 5h 10h 20h
CLO 4 2h 4h 6h
Total SLT 30h 12h 48h 90h

Continuous Assessment PLO Percentage Total SLT

1 Quiz KW 10 1h
2 Assignment PS 15 4h
3 Mid-term Test KW 15 2h
4 Project AD 15 10h
5 Project teamwork AD 5 10h
Final Assessment Percentage Total SLT
1 Final Examination KW 40 3h
Grand Total SLT 120h

Special requirement to deliver the course (e.g: software, nursery, computer lab, simulation room):
Software / Programming Language: Python, Prolog
Hardware: Arduino (optional)

Learning resources:
Text book (if applicable)
Russel, S.J & Norvig, P., Artificial Intelligence: A Modern Approach, Pearson Education, 2016.

Luger, G.F & Stubblefield, W.A, Artificial Intelligence: Structures and Strategies for Complex Problem Solving, 6th
Edition, Addison-Wesley, 2009.

Online
MOOC / E-learning: http://elearning.utm.my

Academic honesty and plagiarism:

Assignments are individual tasks and NOT group activities (UNLESS EXPLICITLY INDICATED AS GROUP ACTIVITIES)
Department/ Software Engineering /Computing Page: 4 of 4
Faculty:
Course code: SCSJ 3553 Academic Session/Semester: 20182019/1

Course name: Artificial Intelligence Pre/co requisite (course name Data Structure
and code, if applicable):
Credit hours: 3

Copying of work (texts, lab results etc.) from other students/groups or from other sources is not allowed. Brief
quotations are allowed and then only if indicated as such. Existing texts should be reformulated with your own words
used to explain what you have read. It is not acceptable to retype existing texts and just acknowledge the source as
a reference. Be warned: students who submit copied work will obtain a mark of zero for the assignment and exams
and disciplinary steps may be taken by the Faculty. It is also unacceptable to do somebody else’s work, to lend your
work to them or to make your work available to them to copy.

Other additional information (Course policy, any specific instruction etc.):

1. Attendance is compulsory and will be taken in every lecture session. Student with less than 80% of total
attendance is not allowed to sit for final exam.
2. Students are required to behave and follow the University’s dressing regulation and etiquette all the time.
3. Exercises and tutorial will be given in class and some may be taken for assessment. Students who do not do the
exercise will lose the coursework marks for the exercise.
4. Assignments must be submitted on the due dates. Some points will be deducted for late submissions.
Assignments submitted three days after the due date will not be accepted.
5. Make up exam will not be given, except to students who are sick and submit medical certificate which is
confirmed by UTM panel doctors. Make up exam can only be given within one week of the initial date of exam.

No. Assessment Total (%) PL01 PLO3 PLO8

Total (%)

CLO1 CLO2 CLO3 CLO4

1 Quiz 1 5.0 5 5.0
2 Quiz 2 5.0 5 5.0
3 Assignment 1 5.0 5 5.0
4 Assignment 2 5.0 4 1 5.0
5 Assignment 3 5.0 4 1 5.0
6 Mid-Term Test 15.0 5 10 15.0
7 Final Exam 40.0 10 15 15 40.0
8 Project Teamwork 5.0 5 5.0
9 Project 15.0 15 10.0
100.0 25.0 30.0 38.0 7.0 100.0
Overall Total (%) 25.0 68.0 7.0

Disclaimer:
No one is allowed to use texts or excerpts from lectures or other teaching and learning activities at Universiti
Teknologi Malaysia except for the purpose of his/her studies. In particular, making copies of the texts or excerpts in
any form at all for the purpose of publication or distribution is strictly forbidden.

While every effort has been made to ensure the accuracy of the information supplied herein, Universiti Teknologi
Malaysia cannot be held responsible for any errors or omissions.