Pattern Recognition and Machine Learning (11482.1)
Available teaching periods | Delivery mode | Location |
---|---|---|
View teaching periods | On-campus |
Bruce, Canberra |
EFTSL | Credit points | Faculty |
0.125 | 3 | Faculty Of Science And Technology |
Discipline | Study level | HECS Bands |
Academic Program Area - Technology | Level 3 - Undergraduate Advanced Unit | Band 2 2021 (Commenced After 1 Jan 2021) Band 3 2021 (Commenced Before 1 Jan 2021) |
This unit may be cotaught with 11512 Pattern Recognition and Machine Learning PG.
Learning outcomes
After successful completion of this unit, students will be able to:1. Understand, describe and critique pattern recognition, machine learning and deep learning techniques;
2. Identify and select suitable modelling, learning and prediction techniques to solve a problem;
3. Design and implement a machine learning solution; and
4. Appraise ethical and privacy issues of artificial intelligence techniques.
Graduate attributes
1. UC graduates are professional - communicate effectively1. UC graduates are professional - display initiative and drive, and use their organisation skills to plan and manage their workload
1. UC graduates are professional - employ up-to-date and relevant knowledge and skills
1. UC graduates are professional - take pride in their professional and personal integrity
1. UC graduates are professional - use creativity, critical thinking, analysis and research skills to solve theoretical and real-world problems
1. UC graduates are professional - work collaboratively as part of a team, negotiate, and resolve conflict
2. UC graduates are global citizens - adopt an informed and balanced approach across professional and international boundaries
2. UC graduates are global citizens - adopt an informed and balanced approach across professional and international boundaries
2. UC graduates are global citizens - behave ethically and sustainably in their professional and personal lives
2. UC graduates are global citizens - communicate effectively in diverse cultural and social settings
2. UC graduates are global citizens - make creative use of technology in their learning and professional lives
2. UC graduates are global citizens - think globally about issues in their profession
2. UC graduates are global citizens - understand issues in their profession from the perspective of other cultures
3. UC graduates are lifelong learners - adapt to complexity, ambiguity and change by being flexible and keen to engage with new ideas
3. UC graduates are lifelong learners - be self-aware
3. UC graduates are lifelong learners - evaluate and adopt new technology
Prerequisites
11372 Introduction to Data Science ORBoth 4478 Introduction to Information Technology and 4483 Software Technology 1
Corequisites
None.Incompatible units
11512 Pattern Recognition and Machine Learning PGEquivalent units
None.Assumed knowledge
None.Year | Location | Teaching period | Teaching start date | Delivery mode | Unit convener |
---|---|---|---|---|---|
2024 | Bruce, Canberra | Semester 2 | 29 July 2024 | On-campus | Prof Dharmendra Sharma |
2025 | Bruce, Canberra | Semester 2 | 28 July 2025 | On-campus | Prof Dharmendra Sharma |
Required texts
No required textbook. Students can consult any on-line or library reference material on the relevant topics. Some useful links are suggested below.
Reference Material Recommended:
- Pattern Classification (2nd. Edition) by R. O. Duda, P. E. Hart and D. Stork, Wiley 2002,
- Hands-On Machine Learning with Scikit-Learn and TensorFlowby, Aurélien Géron, O'Reilly Media, 2017,
- Pattern Recognition and Machine Learning by C. Bishop, Springer 2006,
- Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville,MIT Press 2016,
- Artificial intelligence: a modern approach by Russell, S. J., Norvig, P., & Davis, E. (2010. 3rd ed.) Upper Saddle River, NJ: Prentice Hall. http://aima.cs.berkeley.edu/
- Statistics and the Evaluation of Evidence for Forensic Scientists by C. Aitken and F. Taroni, Wiley, 2004,
- Python Data Science Handbook, Essential Tools for Working with Data, Jake VanderPlas, Publisher: O'Reilly Media, November 2016, and
- Introduction to Machine Learning with Python, Andreas C. Müller and Sarah Guido, A Guide for Data Scientists, Andreas C. Müller and Sarah Guido - O'Reilly, 2016
Submission of assessment items
Special assessment requirements
In PRML, all the assessment items are to be completed either individually or in groups of 2. Students are required to satisfactorily complete all the assessment requirements of the unit. To obtain a particular grade in this unit it is necessary that there are no outstanding submissions at the end of week 14. The unit convener reserves the right to question students orally on any of their submitted work.
All assessment items will receive a numerical mark. The final grade will be determined as a weighted average of the individual assessment items.
To be awarded a particular grade in PRML, students must meet the overall requirements, the assignment requirements and the exam requirements set out in the table below. All grades are conditional upon the following minimum requirements:
Minimum 50% of total available marks from all assessment tasks.
Grade |
Assignments |
Pass |
Minimum 50% of combined weighted marks of all assessment items |
Credit |
Minimum 65% of combined weighted marks of all assessment items |
Distinction |
Minimum 75% of combined weighted marks of all assessment items |
High Distinction |
Minimum 85% of combined weighted marks of all assessment items |
Note: The unit convenor reserves the right to question students on any of their submitted work for moderation and academic integrity purposes, which may result in an adjustment to the marks awarded for a specific task.
Students must apply academic integrity in their learning and research activities at UC. This includes submitting authentic and original work for assessments and properly acknowledging any sources used.
Academic integrity involves the ethical, honest and responsible use, creation and sharing of information. It is critical to the quality of higher education. Our academic integrity values are honesty, trust, fairness, respect, responsibility and courage.
UC students have to complete the Academic Integrity Module annually to learn about academic integrity and to understand the consequences of academic integrity breaches (or academic misconduct).
UC uses various strategies and systems, including detection software, to identify potential breaches of academic integrity. Suspected breaches may be investigated, and action can be taken when misconduct is found to have occurred.
Information is provided in the Academic Integrity Policy, Academic Integrity Procedure, and University of Canberra (Student Conduct) Rules 2023. For further advice, visit Study Skills.
Learner engagement
Activity |
Unit Workload (hrs) - as a guide |
Lectures Attendance (1.5 hrs x 12 weeks) |
18 |
Lectures Preparation (1.5 hrs x 12 weeks) |
18 |
Tutorials/Labs Attendance (2 hr x 11 weeks) |
22 |
Assignment 1 |
25 |
Assignment 2 |
25 |
Assignment 3 – Unit Project |
32 |
Presentation |
10 |
Total |
150 |
Participation requirements
Your participation in lectures, tutorials and online activities will enhance your understanding of the unit content and therefore the quality of your assessment responses. Lack of participation may result in your inability to satisfactorily pass assessment items. So you are urged to fully participate in all the activities in the unit to derive maximum value.
Required IT skills
Specialist IT skills will be required in the unit. Python programming would be the environment used for developing the unit skills and learning outcomes.
This unit involves online meetings in real time using the Virtual Room in your UCLearn teaching site. The Virtual Room allows you to communicate in real time with your lecturer and other students. To participate verbally, rather than just typing, you will need a microphone. For best audio quality we recommend a microphone and speaker headset. For more information and to test your computer, go to the Virtual Room in your UCLearn site and 'Join Course Room'. This will trigger a tutorial to help familiarise you with the functionality of the Virtual Room.
Work placement, internships or practicums
None