COMP307 (2024) - Fundamentals of Artificial Intelligence

Prescription

This course addresses key ideas and techniques of artificial intelligence (AI). It provides a brief introduction to the history of AI and fundamental search techniques, as well as introducing important machine learning topics and algorithms with their applications, including neural networks, and addresses a selection of other important topics in AI.

Course learning objectives

Students who pass this course should be able to:

  1. Understand and explain fundamental concepts and techniques of artificial intelligence, in areas such as search, machine learning, evolutionary computing. (BE 3(a), 3(c), 3(d), 3(e)); (BSc COMP 1, 2, 3, 4).
  2. Apply fundamental concepts and techniques of AI to specific problems (including engineering applications). (BE 3(a), 3(c), 3(d), 3(e), 3(f)); (BSc COMP 1, 2, 3, 4).

Course content

We’ve designed this course for in-person study, and to get the most of out it we strongly recommend you attend lectures on campus. Most assessment items, as well as tutorials/seminars/labs/workshops will only be available in person. Any exceptions for in-person attendance for assessment will be looked at on a case-by-case basis in exceptional circumstances, e.g., through disability services or by approval by the course coordinator.
 
If you started your programme of study remotely and can only study remotely, please contact the School so we can help and confirm what courses are available.  
 
===============================
 
Artificial Intelligence (AI) is intelligence exhibited by machines. Examples include self-driving cars, automatically planning a holiday, generating sensible conversation, learning to predict fog at Wellington Airport, reading a web page to get the answer to a question, recognising handwritten digits, detecting identity by checking fingerprints, detecting network intrusions, controlling robot actuators, processing and recognising images and signals, discovering and detecting the mathematical or logical relationship between output variables and a large number of inputs in economic and engineering tasks, or optimising parameter values in complex engineering problems. COMP 307 is an introduction to the ideas and techniques that computer scientists have developed to address these kinds of tasks.
 
The lectures cover following main topics: search techniques, machine learning including basic learning concepts and algorithms, neural networks and evolutionary learning, reasoning under uncertainty, planning and scheduling, knowledge based systems and AI Philosophy. The course includes a substantial amount of programming. The course will cover both science and engineering applications.

Withdrawal from Course

Withdrawal dates and process:
https://www.wgtn.ac.nz/students/study/course-additions-withdrawals

Lecturers

Dr Heitor Murilo Gomes (Coordinator)

Dr Aaron Chen

Teaching Format

This course will be offered in-person and remotely. For students in Wellington, there will be a combination of in-person components and web/internet based resources. It will also be possible to take the course remotely for those who cannot attend on campus, with recorded lectures made available online.
 
During the trimester there will be typically two lectures and one tutorial per week.

Dates (trimester, teaching & break dates)

  • Teaching: 26 February 2024 - 31 May 2024
  • Break: 01 April 2024 - 14 April 2024
  • Study period: 03 June 2024 - 06 June 2024
  • Exam period: 07 June 2024 - 22 June 2024

Class Times and Room Numbers

26 February 2024 - 24 March 2024

  • Friday 12:00 - 12:50 – LT205, Hugh Mackenzie, Kelburn
26 February 2024 - 31 March 2024

  • Tuesday 12:00 - 12:50 – LT205, Hugh Mackenzie, Kelburn
  • Thursday 12:00 - 12:50 – LT205, Hugh Mackenzie, Kelburn
15 April 2024 - 21 April 2024

  • Thursday 12:00 - 12:50 – LT205, Hugh Mackenzie, Kelburn
15 April 2024 - 02 June 2024

  • Tuesday 12:00 - 12:50 – LT205, Hugh Mackenzie, Kelburn
  • Friday 12:00 - 12:50 – LT205, Hugh Mackenzie, Kelburn
29 April 2024 - 02 June 2024

  • Thursday 12:00 - 12:50 – LT205, Hugh Mackenzie, Kelburn

Other Classes

There will be some scheduled helpdesks.

Required

There is not required textbook for COMP 307. You can learn all the course content from the lecture notes and slides.
 
Some online materials are available on the course website.

A highly recommended reading is the book: Stuart J. Russell and Peter Norvig, Artificial Intelligence. A Modern Approach, Prentice-Hall, NJ (Available at the library and several bookstores and.) A lot of content of the course is from this book.
 
We will also provide a reading list via the course website.

  • Please see Talis.

Mandatory Course Requirements

In addition to achieving an overall pass mark of at least 50%, students must:

  • Submit reasonable attempts for at least three of the four assignments, because the practical application of the range of concepts and techniques in the course to real problems, demonstrated in the assignments, is critical for meeting CLO 2.

If you believe that exceptional circumstances may prevent you from meeting the mandatory course requirements, contact the Course Coordinator for advice as soon as possible.

Assessment

This course will be assessed through assignments and two tests. There will be four assignments, which will involve a combination of programming and discussions.
The marks and feedback will be returned in two weeks after the submission of each assignment.

Assessment ItemDue Date or Test DateCLO(s)Percentage
Assignment 1 (3-4 weeks)Week 5CLO: 1,216%
Assignment 2 (3 weeks)Week 7CLO: 1,215%
Assignment 3 (2-3 weeks)Week 10CLO: 1,210%
Assignment 4 (2 weeks)Week 12CLO: 1,29%
Final TestAssessment periodCLO: 1,250%

Penalties

The penalty for assignments that are handed in late without prior arrangement is one grade reduction per day. Assignments that are more than one week late will not be marked.
 
There are three late days for the assignments. Students can arrange these three late days among the assignments freely.

Extensions

Individual extensions will only be granted in exceptional personal circumstances, and should be negotiated with the course coordinator before the deadline whenever possible. Documentation (eg, medical certificate) may be requested.

Submission & Return

All work should be submitted through the ECS submission system, accessible through the course web pages. Marks and comments will be returned through the ECS marking system, also available through the course web pages.

Workload

In order to maintain satisfactory progress in COMP 307, you should plan to spend an average of 10 hours per week on this course. A plausible and approximate breakdown for these hours would be:

  • Lectures and tutorials: 3 hours
  • Readings, revision/review, and assignments: 7 hours

If assignments are left until the last minute, the amount of work spent in particular weeks may vary greatly.

Teaching Plan

Lecture schedules can be seen from the course website. See https://ecs.wgtn.ac.nz/Courses/COMP307_2024T1/LectureSchedule

Communication of Additional Information

1. Course website: https://ecs.wgtn.ac.nz/Courses/COMP307_2024T1/
2. Course forum
3. Email sent by the lecturers to students at their ecs email addresses.

Offering CRN: 968

Points: 15
Prerequisites: COMP 261 or NWEN 241 or SWEN 221 or at least a B in both DATA 201 and DATA 202; one of (ENGR 123, MATH 151, MATH 161, MATH 277, QUAN 203, STAT 292)
Restrictions: COMP 420, AIML 420, AIML 232, AIML 131
Duration: 26 February 2024 - 23 June 2024
Starts: Trimester 1
Campus: Kelburn