CAB320 Artificial Intelligence
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 code: | CAB320 |
|---|---|
| Prerequisite(s): | (INB270 or CAB201 or ITD121 or CAB202) and (MZB151 or ENB246 or MZB126 or EGD126 or MZB127 or MXB103 or MXB100) |
| Credit points: | 12 |
| Timetable | Details in HiQ, if available |
| Availabilities |
|
| CSP student contribution | $1,118 |
| Domestic tuition unit fee | $4,104 |
| International unit fee | $4,788 |
Unit Outline: Semester 1 2024, Gardens Point, Internal
| Unit code: | CAB320 |
|---|---|
| Credit points: | 12 |
| Pre-requisite: | (INB270 or CAB201 or ITD121 or CAB202) and (MZB151 or ENB246 or MZB126 or EGD126 or MXB103 or MXB100) |
| Coordinator: | Thierry Peynot | t.peynot@qut.edu.au |
Overview
This foundational unit introduces the basics of Artificial Intelligence (AI) ranging from Intelligent Search techniques to Machine Learning. AI strives to build intelligent entities as well as understand them. AI has produced many significant products; from AI chess champions to state-of-the-art schedulers and planners. This unit introduces state representations, techniques and architectures used to build intelligent systems. It covers topics such as heuristic search, machine learning (including deep learning) and probabilistic reasoning. The ability to formalise a given problem in the language/framework of relevant AI methods (for example a search problem, a planning problem or a classification problem) and understand a fast evolving field is a requirement for a range of graduate entry engineer positions. This unit lays the foundations for further studies in Robotics, Pattern Recognition, Computer Vision, Information Retrieval, Data Mining or Intelligent Web Agents.
Learning Outcomes
On successful completion of this unit you will be able to:
- Explain AI methods and theories and how they can be applied to real world problems.
- Analyse search, planning and machine learning problems and formalise them in the language/framework of relevant AI methods.
- Build intelligent artefacts using AI software engineering skills.
- Evaluate empirically different solutions and make fully justified recommendations.
- Collaborate with others in a team environment to deliver an outcome for a client.
- Communicate professionally to produce a report or a presentation for a client.
Content
The following topics will be covered
- Ethics of AI
- Problem solving and search: problem formulation; search space; tree search; graph search. Informed search; heuristic function; admissibility and consistency; deriving heuristics via problem relaxation.
- Planning: forward planning; backward planning; planning heuristics.
- Natural Language Processing
- Playing games: game tree; utility function; optimal strategies; minimax algorithm; alpha-beta pruning; games with an element of chance.
- Introduction to Machine Learning: probabilistic foundations.
- Supervised learning: classification and regression.
- Unsupervised learning.
- Reinforcement learning.
- Introduction to deep learning.
Learning Approaches
This unit is available for you to study in either on-campus or online mode. Learning in this unit includes weekly live or pre-recorded lectures, online or in-person activities, practical sessions and a unit communications channel, designed to facilitate communication with your peers and teaching staff outside of scheduled classes. You can expect to spend about 12 hours per week on average involved in preparing for and attending all scheduled classes, completing assessment tasks, and undertaking your own study to consolidate your learning.
The lectures will introduce you to the key concepts. These key concepts, theory and procedures will be applied in practical sessions where you will engage in collaborative activity with peers and tutors. The practical sessions are focussed on building intelligent artefacts in the context of assignment projects and allow exploration of concepts with teaching staff and other students, and to receive feedback on your progress and understanding.
Feedback on Learning and Assessment
Feedback in this unit is provided to you in the following ways:
- a range of formative exercises will be discussed in class
- comments on summative assessment work in addition to the assessment rubric
- generic comments back to the cohort via QUT Canvas
- criterion reference assessment rubric.
Feedback on the early assessment tasks will be received prior to submission of subsequent assessment.
Assessment
Overview
The assessment for this unit is comprised of two programming assignments and a final exam (formal written examination). The assignments, as described below, requires an integrated understanding of the subject matter, with the exam holistically assessing what you have learned across the semester.
Unit Grading Scheme
7- point scale
Assessment Tasks
Assessment: Search project
The overall aim of this assignment is to build an intelligent agent capable of completing planning tasks and to produce a report to describe your solution to a client.
this assignment is eligible for the 48-hour late submission period and assignment extensions.
Assessment: Machine Learning Project
You will be provided with a data set and you will need to create learning agent based on the dataset. You will then evaluate the different solutions to make and justify recommendations in a client report.
this assignment is eligible for the 48-hour late submission period and assignment extensions.
Assessment: Examination (invigilated)
“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.”
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
Learning material in this unit will be managed from the Canvas site.
Resource Materials
Prescribed text(s)
Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (4th edition), 2020.
Risk Assessment Statement
No particular risk is associated to this unit.
Standards/Competencies
This unit is designed to support your development of the following standards\competencies.
Engineers Australia Stage 1 Competency Standard for Professional Engineer
1: Knowledge and Skill Base
Relates to: Search project, Machine Learning Project, Examination (invigilated)
Relates to: Search project, Machine Learning Project, Examination (invigilated)
Relates to: Machine Learning Project, Examination (invigilated)
2: Engineering Application Ability
Relates to: Search project, Machine Learning Project
Relates to: Search project
Relates to: Search project
Relates to: Search project
3: Professional and Personal Attributes
Relates to: Examination (invigilated)
Relates to: Search project, Machine Learning Project
Unit Outline: Semester 1 2024, Online
| Unit code: | CAB320 |
|---|---|
| Credit points: | 12 |
| Pre-requisite: | (INB270 or CAB201 or ITD121 or CAB202) and (MZB151 or ENB246 or MZB126 or EGD126 or MXB103 or MXB100) |
Overview
This foundational unit introduces the basics of Artificial Intelligence (AI) ranging from Intelligent Search techniques to Machine Learning. AI strives to build intelligent entities as well as understand them. AI has produced many significant products; from AI chess champions to state-of-the-art schedulers and planners. This unit introduces state representations, techniques and architectures used to build intelligent systems. It covers topics such as heuristic search, machine learning (including deep learning) and probabilistic reasoning. The ability to formalise a given problem in the language/framework of relevant AI methods (for example a search problem, a planning problem or a classification problem) and understand a fast evolving field is a requirement for a range of graduate entry engineer positions. This unit lays the foundations for further studies in Robotics, Pattern Recognition, Computer Vision, Information Retrieval, Data Mining or Intelligent Web Agents.
Learning Outcomes
On successful completion of this unit you will be able to:
- Explain AI methods and theories and how they can be applied to real world problems.
- Analyse search, planning and machine learning problems and formalise them in the language/framework of relevant AI methods.
- Build intelligent artefacts using AI software engineering skills.
- Evaluate empirically different solutions and make fully justified recommendations.
- Collaborate with others in a team environment to deliver an outcome for a client.
- Communicate professionally to produce a report or a presentation for a client.
Content
The following topics will be covered
- Ethics of AI
- Problem solving and search: problem formulation; search space; tree search; graph search. Informed search; heuristic function; admissibility and consistency; deriving heuristics via problem relaxation.
- Planning: forward planning; backward planning; planning heuristics.
- Natural Language Processing
- Playing games: game tree; utility function; optimal strategies; minimax algorithm; alpha-beta pruning; games with an element of chance.
- Introduction to Machine Learning: probabilistic foundations.
- Supervised learning: classification and regression.
- Unsupervised learning.
- Reinforcement learning.
- Introduction to deep learning.
Learning Approaches
This unit is available for you to study in either on-campus or online mode. Learning in this unit includes weekly live or pre-recorded lectures, online or in-person activities, practical sessions and a unit communications channel, designed to facilitate communication with your peers and teaching staff outside of scheduled classes. You can expect to spend about 12 hours per week on average involved in preparing for and attending all scheduled classes, completing assessment tasks, and undertaking your own study to consolidate your learning.
The lectures will introduce you to the key concepts. These key concepts, theory and procedures will be applied in practical sessions where you will engage in collaborative activity with peers and tutors. The practical sessions are focussed on building intelligent artefacts in the context of assignment projects and allow exploration of concepts with teaching staff and other students, and to receive feedback on your progress and understanding.
Feedback on Learning and Assessment
Feedback in this unit is provided to you in the following ways:
- a range of formative exercises will be discussed in class
- comments on summative assessment work in addition to the assessment rubric
- generic comments back to the cohort via QUT Canvas
- criterion reference assessment rubric.
Feedback on the early assessment tasks will be received prior to submission of subsequent assessment.
Assessment
Overview
The assessment for this unit is comprised of two programming assignments and a final exam (formal written examination). The assignments, as described below, requires an integrated understanding of the subject matter, with the exam holistically assessing what you have learned across the semester.
Unit Grading Scheme
7- point scale
Assessment Tasks
Assessment: Search project
The overall aim of this assignment is to build an intelligent agent capable of completing planning tasks and to produce a report to describe your solution to a client.
this assignment is eligible for the 48-hour late submission period and assignment extensions.
Assessment: Machine Learning Project
You will be provided with a data set and you will need to create learning agent based on the dataset. You will then evaluate the different solutions to make and justify recommendations in a client report.
this assignment is eligible for the 48-hour late submission period and assignment extensions.
Assessment: Examination (invigilated)
“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.”
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
Learning material in this unit will be managed from the Canvas site.
Resource Materials
Prescribed text(s)
Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach (4th edition), 2020.
Risk Assessment Statement
No particular risk is associated to this unit.
Standards/Competencies
This unit is designed to support your development of the following standards\competencies.
Engineers Australia Stage 1 Competency Standard for Professional Engineer
1: Knowledge and Skill Base
Relates to: Search project, Machine Learning Project, Examination (invigilated)
Relates to: Search project, Machine Learning Project, Examination (invigilated)
Relates to: Machine Learning Project, Examination (invigilated)
2: Engineering Application Ability
Relates to: Search project, Machine Learning Project
Relates to: Search project
Relates to: Search project
Relates to: Search project
3: Professional and Personal Attributes
Relates to: Examination (invigilated)
Relates to: Search project, Machine Learning Project