Course Outline

Contents

• Course Details
• Timetable
• Course Summary
• Assumed Knowledge
• Student Learning Outcomes
• Teaching
• Assessment
• Resources for Students
• Student Conduct
• Course Evaluation and Development

Course Details

Course Code	COMP3411/9814
Course Title	Artificial Intelligence
Units of Credit	6
Course Website	http://www.cse.unsw.edu.au/~cs3411
Handbook Entry	http://www.handbook.unsw.edu.au/undergraduate/courses/current/COMP3411.html
Lecturer-in-Charge	Claude Sammut <cs3411@cse.unsw.edu.au>
Lecturers	Claude Sammut, Armin Chitizadeh, Francisco Cruz
Course Admin	Tatjana Zrimec <cs3411@cse.unsw.edu.au>

Timetable

	Monday	Tuesday	Wednesday		Thursday		Friday
09:00 - 10:00
10:00 - 11:00			Tut - W10A		Tut - H10A		Tut - F10A
11:00 - 12:00			Tut - W11A		Tut - H11A		Tut - F11A
12:00 - 1300			Tut - W12A		Tut - H12A		Lecture in-person (Mathews A) online
13:00 - 14:00
14:00 - 15:00			Tut - W14A		Tut - H14A		Tut - F14A
15:00 - 16:00			Tut - W15A		Tut - H15A
16:00 - 17:00		Lecture in-person (Mathews A) online	Tut - W16A		Tut - H16A online
17:00 - 18:00			Tut - W17B online	Tut - W17B	Tut - H17A online	Tut - H17B online
18:00 - 19:00			Tut - W18A online		Tut - H18A- online

Course Summary

Artificial Intelligence is concerned with the design and construction of computer systems that "think". This course will introduce students to the main ideas and approaches in AI - including agent architectures, AI programming, search techniques, knowledge representation and reasoning, machine learning, natural language processing, logical inference and robotics.

This course will introduce you to the following main ideas and approaches in AI:

1. Artificial Intelligence, Intelligent Agents

• Introduction and history of AI
• Agents and Autonomous Systems

2. Knowledge and Reasoning

• Path Search
• Heuristic Path Search
• Constraint Satisfaction
• Logical Agents and Logic Programming
• Uncertainty

3. Machine Learning

• Learning and Decision Trees
• Reinforcement Learning and Neural Networks

4. Additional topics:

• Natural Language Processing
• Computer Visions
• Robotics

The approach to the presentation of the material will be to start be describing simple agents with limited sensing and intelligence and progressing to increasingly complex agents. The topics above will be introduced, as needed by each type of agent.

Assumed Knowledge

COMP3411

Pre-requisite: COMP1927 or COMP2521

COMP9814

Pre-requisite: COMP9024

Student Learning Outcomes

Students successfully completing this course will:

• Gain a working knowledge of fundamental AI methods and techniques.
• Be able to demonstrate knowledge of AI methods by explaining certain features or aspects of these algorithms.
• Describe how the techniques would be applied to particular problems.
• Develop competency in the AI programming.
• Gain practical experience through the assignments to understand what is involved in designing and implementing a functional AI system.

Teaching

There will be four hours of lectures per week, plus one hour of tutorial. The major AI algorithms and learning techniques will be presented in lectures and illustrated on sample problems, along with historical background and theoretical motivation.

Tutorials give students a chance to clarify the ideas mentioned in lectures and practice their problem-solving skills in a small (and hopefully more personal) class with the assistance of a tutor. Students are expected to prepare for and actively participate in tutorials. Most tutorials will also include one or two questions of a speculative nature - which can lead to more in-depth discussion of particular topics, depending on the interests of the students.

Assessment

The assessable components of the course are:

Component	Mark
3 Assignments (30%) + 5 Quizzes (10%)	40%
Written Exam	60%

Further details about the assignments will be posted on the Course Web site. Programming assignments give the students an opportunity to put into practice the ideas and approaches that have been presented in lectures and discussed in tutorials. They may, for example, involve writing a program to:

• enable an agent to act in a simulated environment
• solve a problem using search techniques
• play a game
• apply a machine learning algorithm
• enable communication or co-operation between agents

In order to pass the course, students must score:

• at least 16/40 for the assignments and quizzes
• at least 24/60 for the exam
• a combined mark of at least 50/100

Assignments

Assignments	Starting Date	Due Date
Assignment - 1	Tuesday, 21/02/23	Thursday, 09/03/23, 10 pm
Assignment - 2	Friday, 10/03/23	Thursday, 30/03/23, 10 pm
Assignment - 3	Friday, 31/03/23	Friday, 21/04/23, 10 pm

Quizzes

Quiz	Starting Date	Time	Due Date	Time	Weeks
Quiz 1	Tue 21/2/2023	18:00	Tue 28/2/2023	18:00	W2 - W3
Quiz 2	Fri 3/3/2023	18:00	Fri 10/3/2023	23:55	W3 - W4
Quiz 3	Fri 10/3/2023	18:00	Fri 17/3/2023	23:55	W4 - W5
Quiz 4	Fri 17/3/2023	18:00	Fri 31/3/2023	23:55	W5 - W7
Quiz 5	Tue 4/4/2023	18:00	Fri 14/4/2023	23:55	W8 - W9

Course Schedule

Introduction to AI and Search	week 1
Search	week 2
Reinforcement Learning	week 3
Robot Vision and Neural Networks	week 4
Knowledge Representation	week 5
Machine Learning	week 7
Planning	week 8
Reasoning under Uncertainty	week 9
Communicating agents, Course review	week 10

Resources for Students

The recommended textbooks for this course are:

• David L. Poole and Alan K. Mackworth Artificial Intelligence: Foundations of Computational Agents , 2nd Edition
• Nils J. Nilsson, Artificial Intelligence: a New Synthesis , Morgan Kaufmann, 1998, ISBN 1-55860-467-7.

There are electronic versions of the books, as well as print. Here are the links to Poole & Mackworth:

• Print - https://www.bookshop.unsw.edu.au/details.cgi?ITEMNO=9781107195394
• Digital - https://artint.info/2e/html/ArtInt2e.html

and for Nilsson:

• Digital - https://www-sciencedirect-com.wwwproxy1.library.unsw.edu.au/book/9781558604674/artificial-intelligence-a-new-synthesis

The following books might also serve as additional reference material:

• Stuart Russell and Peter Norvig, Artificial Intelligence: a Modern Approach , 3th Ed., Prentice Hall, 2010.
• Ivan Bratko, Prolog Programming for Artificial Intelligence , 4th Edition, Pearson, 2013.
• Valentino Braitenberg, Vehicles: Experiments in Synthetic Psychology , MIT Press, 1984, ISBN 0-262-52112-1.

Links to other electronic resources will be provided on the course web page throughout the session.

Student Conduct

The Student Code of Conduct ( Information , Policy ) sets out what the University expects from students as members of the UNSW community. As well as the learning, teaching and research environment, the University aims to provide an environment that enables students to achieve their full potential and to provide an experience consistent with the University's values and guiding principles. A condition of enrolment is that students inform themselves of the University's rules and policies affecting them, and conduct themselves accordingly.

In particular, students have the responsibility to observe standards of equity and respect in dealing with every member of the University community. This applies to all activities on UNSW premises and all external activities related to study and research. This includes behaviour in person as well as behaviour on social media, for example Facebook groups set up for the purpose of discussing UNSW courses or course work. Behaviour that is considered in breach of the Student Code Policy as discriminatory, sexually inappropriate, bullying, harassing, invading another's privacy or causing any person to fear for their personal safety is serious misconduct and can lead to severe penalties, including suspension or exclusion from UNSW.

If you have any concerns, you may raise them with your lecturer, or approach the School Ethics Officer , Grievance Officer , or one of the student representatives.

Plagiarism is defined as using the words or ideas of others and presenting them as your own. UNSW and CSE treat plagiarism as academic misconduct, which means that it carries penalties as severe as being excluded from further study at UNSW. There are several on-line sources to help you understand what plagiarism is and how it is dealt with at UNSW:

• Plagiarism and Academic Integrity
• UNSW Plagiarism Procedure

Make sure that you read and understand these. Ignorance is not accepted as an excuse for plagiarism. In particular, you are also responsible that your assignment files are not accessible by anyone but you by setting the correct permissions in your CSE directory and code repository, if using. Note also that plagiarism includes paying or asking another person to do a piece of work for you and then submitting it as your own work.

UNSW has an ongoing commitment to fostering a culture of learning informed by academic integrity. All UNSW staff and 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.

Artificial intelligence tools such as ChatGPT, CodePilot, CoPilot, and built-in functions within Word are modern tools that are useful in some circumstances, but reliance on them is not a path to success at university or in your later career. Reaching for a calculator to add up 1+1 is possible but not professionally sustainable for an engineer or scientist (or one might say in our educated society at all!), and that is why you learnt to do that yourself at primary school. Likewise, in your degree at UNSW, we're teaching you skills that are needed for your professional life, which is a combination of some things that AI could feasibly do for you and lots of things that the AI tools cannot do for you — if we were only teaching you things that AI could do, your degree would be worthless and you wouldn't have a job in 5 years. You can therefore see that from an academic standards perspective, the output from an AI tool will be below the minimum standards expected for a course, even if you were to submit it (which you should not!). Your ability to complete later assessments where AI cannot help you will also be compromised if you've relied upon AI earlier.

It is also worth remembering what these AI tools such as ChatGPT are: they are only statistical models about how groups of words frequently appear. These AI based tools are not smart, they don't know anything other than how words are often grouped, and they most certainly do not understand any of the content from any of your courses. Some consequences of their word-statistics and non-scientific basis are:

• They generate confident-sounding text that is completely wrong from a technical point of view.
• The text mangles jargon very badly.
• The output gets causality backwards and so often argues completely the wrong thing.
• The output will include unit conversions but it will often get them wrong.
• The generated text is often very generic, bland, lacking on detail, and not actually very helpful.
• The output is often just a collection of loosely related factual-sounding sentences that don't answer the question that was actually asked.

In summary, the AI tools generate text output that is superficially reasonable, very confident sounding, and very often wrong. We are setting an expectation that our graduates should out-perform AI, meaning that it is a tool of limited academic use in your degree.

If you haven't done so yet, please take the time to read the full text of

• UNSW's policy regarding academic honesty and plagiarism

The pages below describe the policies and procedures in more detail:

• Student Code Policy
• Student Misconduct Procedure
• Plagiarism Policy Statement
• Plagiarism Procedure

Course Evaluation and Development

This course is evaluated each session using the myExperience system.

In the previous offering of this course, students noted that the webcsm3 forums were less than optimal and that it was difficult to get engaged (with other students) online. Students also noted that their questions were answered with delays.

The Webcms3 forum have been re-written to incorporate the requested features. This term, we also hired three tutors and a course admin to answer the forum in addition to the three lecturers of the course.

Students also noted that there were not enough assessment through out the term and they received late feedback for their assignments. To address this, we introduced three auto-marked assignments to this course. We also introduced five quizzes which will familiarise students with the final exam.

Students are always welcome to provide feedback at any point in the term on their experience by emailing the course account or completing the feedback form linked in the sidebar.