UNSW Course Outline
COMP9414 Artificial Intelligence -
2024
Published on the 21 May 2024
General Course Information
Course Code : COMP9414
Year : 2024
Term : Term 2
Teaching Period : T2
Is a multi-term course? : No
Faculty : Faculty of Engineering
Academic Unit : School of Computer Science and Engineering
Delivery Mode : In Person
Delivery Format : Standard
Delivery Location : Kensington
Campus : Sydney
Study Level : Postgraduate
Units of Credit : 6
Useful Links
Handbook Class Timetable
Course Details & Outcomes
Course Description
COMP9414 is an introductory course on Artificial Intelligence covering fundamental topics such
as autonomous agents, problem solving, optimisation, logic, knowledge representation,
reasoning under uncertainty, vision, language processing, machine learning, neural networks and
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 1 of 11
reinforcement learning. The course is taught with an orientation towards machine learning and
with a view to practical applications of Artificial Intelligence using Python. Some AI applications
that make use of foundational concepts will be demonstrated in lectures and tutorials.
Course Aims
The course aims to provide a foundation for further studies in AI such as COMP4418 Knowledge
Representation and Reasoning, COMP9417 Machine Learning and Data Mining, COMP9517
Computer Vision, COMP9434 Robotic Software Architecture, and COMP9444 Neural Networks
and Deep Learning. Postgraduate students with more programming experience may consider
enrolling in COMP9814, which is the same as the undergraduate AI course COMP3411 (offered
in Term 1).
Course Learning Outcomes
Course Learning Outcomes
CLO1 : Demonstrate understanding of the foundations of AI and fundamental AI techniques
CLO2 : Choose appropriate AI techniques to solve given problems and implement standard AI
algorithms
CLO3 : Demonstrate practical skills in utilizing AI toolkits in realistic application areas
CLO4 : Evaluate the risks of applying AI in business and industry
Course Learning Outcomes Assessment Item
CLO1 : Demonstrate understanding of the foundations of AI • Assignment 2
and fundamental AI techniques • Assignment 1
• Exam
CLO2 : Choose appropriate AI techniques to solve given • Assignment 2
problems and implement standard AI algorithms • Assignment 1
• Exam
CLO3 : Demonstrate practical skills in utilizing AI toolkits in • Assignment 2
realistic application areas • Assignment 1
• Exam
CLO4 : Evaluate the risks of applying AI in business and • Assignment 2
industry • Assignment 1
• Exam
Learning and Teaching Technologies
Moodle - Learning Management System
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 2 of 11
Assessments
Assessment Structure
Assessment Item Weight Relevant Dates
Assignment 2 25% Start Date: Not Applicable
Assessment Format: Individual Due Date: Week 5: 24 June - 30 June
Assignment 1 25% Start Date: Not Applicable
Assessment Format: Individual Due Date: Week 9: 22 July - 28 July
Exam 50% Due Date: TBA - Exam Period
Assessment Format: Individual
Assessment Details
Assignment 2
Assessment Overview
This programming assignment is marked based on its correctness and on programming style
and critical analysis. Students can work on the assignment individually or along with a classmate
from the same tutorial. In terms of assessment of correctness and style, there will be no
differences in works made by 1 or 2 students. However, for the analysis and discussion, both
students must participate. It is the student's responsibility to ensure that the submitted code
runs on the school environment using the version of Python installed in the labs.
Weighting:
Results 12.5%
Discussion 12.5%
Feedback:
Students will receive feedback from tutors during the discussion session. In these sessions,
students will demonstrate their code understanding while tutors will provide additional
comments on individual students' solutions.
Course Learning Outcomes
CLO1 : Demonstrate understanding of the foundations of AI and fundamental AI techniques
CLO2 : Choose appropriate AI techniques to solve given problems and implement standard AI
algorithms
CLO3 : Demonstrate practical skills in utilizing AI toolkits in realistic application areas
CLO4 : Evaluate the risks of applying AI in business and industry
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 3 of 11
Assignment submission Turnitin type
Not Applicable
Assignment 1
Assessment Overview
This programming assignment is marked based on its correctness and on programming style
and critical analysis. Students can work on the assignment individually or along with a classmate
from the same tutorial. In terms of assessment of correctness and style, there will be no
differences in works made by 1 or 2 students. However, for the analysis and discussion, both
students must participate. It is the student's responsibility to ensure that the submitted code
runs on the school environment using the version of Python installed in the labs.
Weighting:
Results 12.5%
Discussion 12.5%
Feedback:
Students will receive feedback from tutors during the discussion session. In these sessions,
students will demonstrate their code understanding while tutors will provide additional
comments on individual students' solutions.
Course Learning Outcomes
CLO1 : Demonstrate understanding of the foundations of AI and fundamental AI techniques
CLO2 : Choose appropriate AI techniques to solve given problems and implement standard AI
algorithms
CLO3 : Demonstrate practical skills in utilizing AI toolkits in realistic application areas
CLO4 : Evaluate the risks of applying AI in business and industry
Assignment submission Turnitin type
Not Applicable
Exam
Assessment Overview
The final exam is a 2-hour examination covering all topics in the course.
Course Learning Outcomes
CLO1 : Demonstrate understanding of the foundations of AI and fundamental AI techniques
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 4 of 11
CLO2 : Choose appropriate AI techniques to solve given problems and implement standard AI
algorithms
CLO3 : Demonstrate practical skills in utilizing AI toolkits in realistic application areas
CLO4 : Evaluate the risks of applying AI in business and industry
General Assessment Information
Grading Basis
Standard
Course Schedule
Attendance Requirements
Students are strongly encouraged to attend all classes and review lecture recordings.
General Schedule Information
Week 1 Introduction
1.1 History of AI
1.2 Agents
1.3 Knowledge representation
1.3.1 Feature-based vs iconic representations
1.3.2 Logic
1.3.3 Learning rules
Week 2 Neural Networks
2.1 Neurons - biological and artificial
2.2 Single-layer perceptron
2.3 Linear separability
2.4 Multi-layer networks
2.5 Backpropagation
2.6 Neural engineering methodology
Week 3 Search
3.1 Uninformed search
3.2 Informed search
3.3 Informed vs uninformed
Week 4 Rewards instead of goals
4.1 Elements of reinforcement learning
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 5 of 11
4.2 Exploration vs exploitation
4.3 The agent-environment interface
4.4 Values functions
4.5 Temporal-difference prediction
Week 5 Metaheuristics
5.1 Asymptotic complexity
5.2 Classes of problems
5.3 Linear programming
5.4 Search space
5.5 Metaheuristics with and without memory
5.6 Population-based methods
Week 6 Recap and consultation
Week 7 Computer vision
7.1 Image processing
7.2 Scene analysis
7.3 Cognitive vision
Week 8 Language processing
8.1 Formal languages
8.1.1 Chomsky’s hierarchy
8.1.2 Grammars
8.2 Regular expressions
8.3. Minimum edit distance and words
8.4 Natural languages: N-gram models
Week 9 Reasoning with uncertain information
9.1 Confidence factors
9.1 Probability and probabilistic inference
9.2 Bayes nets
9.3 Fuzzy logic
Week 10 Human-aligned intelligent robotics
10.1 Human interaction and human-in-the-loop robot learning
10.2 Explainability and interpretability
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 6 of 11
10.3 Safe robot exploration
10.4 Ethics
Course Resources
Recommended Resources
- Poole, D.L. & Mackworth, A. Artificial Intelligence: Foundations of Computational Agents.
Second Edition. Cambridge University Press, Cambridge, 2017.
- Russell, S.J. & Norvig, P. Artificial Intelligence: A Modern Approach. Fourth Edition, Pearson
Education, Hoboken, NJ, 2021.
- Sutton, R. & Barto, A. Reinforcement Learning: An Introduction. MIT press. 2018.
- Jurafsky, D. & Martin, J. H. Speech and Language Processing. Stanford. 2023.
- Nilsson, N. J. Artificial intelligence: a new synthesis. Morgan Kaufmann. 1998.
- Aloimonos, Y., & Sandini, G. Principles of Cognitive Vision. In Cangelosi, A., & Asada, M. (Eds.).
Cognitive robotics. MIT Press. 2022.
Staff Details
Position Name Email Location Phone Availability Equitable Learning Primary
Services Contact Contact
Convenor Francisco Cru No No
z
Administrator Maryam Hash Yes Yes
emi
Other Useful Information
Academic Information
I. Special consideration and supplementary assessment
If you have experienced an illness or misadventure beyond your control that will interfere with
your assessment performance, you are eligible to apply for Special Consideration prior to, or
within 3 working days of, submitting an assessment or sitting an exam.
Please note that UNSW has a Fit to Sit rule, which means that if you sit an exam, you are
declaring yourself fit enough to do so and cannot later apply for Special Consideration.
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 7 of 11
For details of applying for Special Consideration and conditions for the award of supplementary
assessment, please see the information on UNSW’s Special Consideration page.
II. Administrative matters and links
All students are expected to read and be familiar with UNSW guidelines and polices. In particular,
students should be familiar with the following:
Attendance
UNSW Email Address
Special Consideration
Exams
Approved Calculators
Academic Honesty and Plagiarism
Equitable Learning Services
III. Equity and diversity
Those students who have a disability that requires some adjustment in their teaching or learning
environment are encouraged to discuss their study needs with the course convener prior to, or at
the commencement of, their course, or with the Equity Officer (Disability) in the Equitable
Learning Services. Issues to be discussed may include access to materials, signers or note-
takers, the provision of services and additional exam and assessment arrangements. Early
notification is essential to enable any necessary adjustments to be made.
IV. Professional Outcomes and Program Design
Students are able to review the relevant professional outcomes and program designs for their
streams by going to the following link: https://www.unsw.edu.au/engineering/student-life/
student-resources/program-design.
Note: This course outline sets out the description of classes at the date the Course Outline is
published. The nature of classes may change during the Term after the Course Outline is published.
Moodle or your primary learning management system (LMS) should be consulted for the up-to-date
class descriptions. If there is any inconsistency in the description of activities between the
University timetable and the Course Outline/Moodle/LMS, the description in the Course Outline/
Moodle/LMS applies.
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 8 of 11
Academic Honesty and Plagarism
UNSW has an ongoing commitment to fostering a culture of learning informed by academic
integrity. All UNSW students have a responsibility to adhere to this principle of academic
integrity. Plagiarism undermines academic integrity and is not tolerated at UNSW. Plagiarism at
UNSW is defined as using the words or ideas of others and passing them off as your own.
Plagiarism is a type of intellectual theft. It can take many forms, from deliberate cheating to
accidentally copying from a source without acknowledgement. UNSW has produced a website
with a wealth of resources to support students to understand and avoid plagiarism, visit:
student.unsw.edu.au/plagiarism. The Learning Centre assists students with understanding
academic integrity and how not to plagiarise. They also hold workshops and can help students
one-on-one.
You are also reminded that careful time management is an important part of study and one of
the identified causes of plagiarism is poor time management. Students should allow sufficient
time for research, drafting and the proper referencing of sources in preparing all assessment
tasks.
Repeated plagiarism (even in first year), plagiarism after first year, or serious instances, may also
be investigated under the Student Misconduct Procedures. The penalties under the procedures
can include a reduction in marks, failing a course or for the most serious matters (like plagiarism
in an honours thesis or contract cheating) even suspension from the university. The Student
Misconduct Procedures are available here:
www.gs.unsw.edu.au/policy/documents/studentmisconductprocedures.pdf
Submission of Assessment Tasks
Work submitted late without an approved extension by the course coordinator or delegated
authority is subject to a late penalty of five percent (5%) of the maximum mark possible for that
assessment item, per calendar day.
The late penalty is applied per calendar day (including weekends and public holidays) that the
assessment is overdue. There is no pro-rata of the late penalty for submissions made part way
through a day. This is for all assessments where a penalty applies.
Work submitted after five days (120 hours) will not be accepted and a mark of zero will be
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 9 of 11
awarded for that assessment item.
For some assessment items, a late penalty may not be appropriate. These will be clearly
indicated in the course outline, and such assessments will receive a mark of zero if not
completed by the specified date. Examples include:
Weekly online tests or laboratory work worth a small proportion of the subject mark;
Exams, peer feedback and team evaluation surveys;
Online quizzes where answers are released to students on completion;
Professional assessment tasks, where the intention is to create an authentic assessment that
has an absolute submission date; and,
Pass/Fail assessment tasks.
Faculty-specific Information
Engineering Student Support Services – The Nucleus - enrolment, progression checks, clash
requests, course issues or program-related queries
Engineering Industrial Training – Industrial training questions
UNSW Study Abroad – study abroad student enquiries (for inbound students)
UNSW Exchange – student exchange enquiries (for inbound students)
UNSW Future Students – potential student enquiries e.g. admissions, fees, programs, credit
transfer
Phone
(+61 2) 9385 8500 – Nucleus Student Hub
(+61 2) 9385 7661 – Engineering Industrial Training
(+61 2) 9385 3179 – UNSW Study Abroad and UNSW Exchange (for inbound students)
School Contact Information
CSE Help! - on the Ground Floor of K17
For assistance with coursework assessments.
The Nucleus Student Hub - https://nucleus.unsw.edu.au/en/contact-us
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 10 of 11
Course enrolment queries.
If the course convenor gives an inadequate response to a query or when the courses
convenor does not respond to a query about assessment.
If some aspect of a course needs urgent improvement. (e.g. Nobody responding to forum
queries, cannot understand the lecturer)
You should never contact any of the following people directly:
- Vice Chancellor
- Pro-vice Chancellor Education (PVCE)
- Head of School
- CSE administrative staff
- CSE teaching support staff
They will simply bounce the email to one of the above, thereby creating an unnecessary level of
indirection and a delay in the response.
COMP9414 Artificial Intelligence - 2024 Printed: 19/2/2025 | 11 of 11
