IFN680 Artificial Intelligence and Machine Learning


To view more information for this unit, select Unit Outline from the list below. Please note the teaching period for which the Unit Outline is relevant.


Unit Outline: Semester 2 2024, Gardens Point, Internal

Unit code:IFN680
Credit points:12
Pre-requisite:(IFN509 or IFQ509) or (192cps in IV04 or enrolment in IV54) or (192cps in EV08 or enrolment in IV58) or (192cps in MV05 or enrolment in IV55)
Assumed Knowledge:

Knowledge of a programming language like Python, Java, C# or C is assumed plus Introductory level knowledge of artificial intelligence

Coordinator:Dimity Miller | d24.miller@qut.edu.au
Disclaimer - Offer of some units is subject to viability, and information in these Unit Outlines is subject to change prior to commencement of the teaching period.

Overview

This is a specialisation unit in the area of computer science and data analytics. The aim of this unit is to provide you with the knowledge and skills required to design and implement artificial intelligence and machine learning solutions that can effectively and efficiently solve complex problems. The main advantage of intelligent systems is that they can combine the traditional computer's capacity to remember millions of facts with the human being's cognitive skills, including learning and refining the existing body of knowledge, solving problems with reasoning, helping businesses with strategic planning, diagnosing mechanical faults or human diseases, playing games, and so on. This unit will provide you with an understanding of the principles and basic techniques to develop artificial intelligence and machine learning, as well as an understanding of the strengths and limitations of these algorithms.

Learning Outcomes

On successful completion of this unit you will be able to:

  1. Explain the fundamental theory underpinning various AI and ML techniques and algorithms, and identify their applications and limitations.
  2. Work independently and in a team to implement and apply appropriate AI and ML techniques to solve specific problems.
  3. Critically evaluate, synthesise, and critique the performance, strengths and limitations of AI and ML methods for given problems.
  4. Communicate your results and the limitations of your models professionally with peers and the stakeholder community.

Content

This unit then introduces concepts, models, and algorithms in the areas of:

1. graphs and search strategies
2. classic machine learning
3. deep learning
4. supervised, unsupervised and reinforcement learning

Basic implementations of these algorithms will be introduced, and case studies on real problems in decision-making, classification and prediction will be covered.

Learning Approaches

This unit will be delivered with a theory-to-practice approach. Each week, you will have a 2-hour lecture, which provides you with the theoretical knowledge required for this unit. You will also have a tutorial where you will apply the theory introduced in lectures with programming to solve various problems. You will be guided through the programming problems, with consolidation of how the theory relates to the practical implementation and guided analysis of the results. For the assignments, you will be required to work individually and in pairs to solve more complex problems which will relate to industry applications with real world datasets.

Feedback on Learning and Assessment

Feedback in this unit will be provided in the following ways:

  • Formative oral feedback will be offered by the lecturer and tutors during the semester to assist you in the development of your skills.
  • Formative written feedback through marking rubric.
  • In addition to criteria and standards in a marking rubric, comments on summative assessment will be provided.
  • Generic comments will be provided to the cohort through the Canvas.

Teaching staff are available for feedback and advice in the practical sessions.

Assessment

Overview

The assessment of this unit includes two projects and a final examination. The first project is designed for you to demonstrate your understanding of the machine learning techniques introduced in this unit as well as your practical implementation skills. You will be required to implement a machine learning algorithm/s to solve a given problem and present your solution in an oral presentation. The second project will require you to work in a team to apply one or more artificial intelligence techniques to solve a given problem and communicate your results and design process in a report. The final examination will allow you to demonstrate your overall knowledge that you obtain from this unit.

Unit Grading Scheme

7- point scale

Assessment Tasks

Assessment: Project 1

In this project, you will identify and implement existing machine learning algorithms to solve an image classification problem. You will be assessed on your implementation and its performance. You must also analyse the performance of your chosen algorithms and communicate your findings in an oral presentation.

Weight: 30
Length: 5 Weeks
Individual/Group: Individual
Due (indicative): Week 7
Related Unit learning outcomes: 1, 2, 3, 4

Assessment: Project 2

In this project, you will design and implement AI reasoning strategies and techniques to solve a given problem. You will detail the process of designing and refining your solution in a report.

This is an assignment for the purposes of an extension.

Weight: 30
Length: 5 weeks
Individual/Group: Group
Due (indicative): Week 13
Related Unit learning outcomes: 2, 3, 4

Assessment: Examination (written)

Written quiz with multiple-choice and short answer questions.

On Campus invigilated Exam. If campus access is restricted at the time of the central examination period/due date, an alternative, which may be a timed online assessment, will be offered. Individual students whose circumstances prevent their attendance on campus will be provided with an alternative assessment approach.

Weight: 40
Individual/Group: Individual
Due (indicative): Central Examination Period
Exam Period
Related Unit learning outcomes: 1, 3

Academic Integrity

Students are expected to engage in learning and assessment at QUT with honesty, transparency and fairness. Maintaining academic integrity means upholding these principles and demonstrating valuable professional capabilities based on ethical foundations.

Failure to maintain academic integrity can take many forms. It includes cheating in examinations, plagiarism, self-plagiarism, collusion, and submitting an assessment item completed by another person (e.g. contract cheating). It can also include providing your assessment to another entity, such as to a person or website.

You are encouraged to make use of QUT’s learning support services, resources and tools to assure the academic integrity of your assessment. This includes the use of text matching software that may be available to assist with self-assessing your academic integrity as part of the assessment submission process.

Further details of QUT’s approach to academic integrity are outlined in the Academic integrity policy and the Student Code of Conduct. Breaching QUT’s Academic integrity policy is regarded as student misconduct and can lead to the imposition of penalties ranging from a grade reduction to exclusion from QUT.

Resources

Resource Materials

Recommended text(s)

  • Textbook
    o Stuart J. Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, (4th edition), 2020

Risk Assessment Statement

There are no unusual health or safety risks associated with this unit