APP MTH 4052 - Applied Mathematics Topic F - Honours
North Terrace Campus - Semester 2 - 2024
-
General Course Information
Course Details
Course Code APP MTH 4052 Course Applied Mathematics Topic F - Honours Coordinating Unit Mathematical Sciences Term Semester 2 Level Undergraduate Location/s North Terrace Campus Units 3 Contact Up to 2.5 hours per week Available for Study Abroad and Exchange Y Restrictions Honours students only Assessment Ongoing assessment, exam Course Staff
Course Coordinator: Professor Matthew Roughan
This is the same course as APP MTH 7088 - Applied Mathematics Topic FCourse Timetable
The full timetable of all activities for this course can be accessed from Course Planner.
-
Learning Outcomes
Course Learning Outcomes
This year the topic will be "Mathematics of Artificial Intelligence". This course will be co-taught between the School of Mathematics and the Australian Institute of Machine Learning. It will be split into 3 modules:
Module 1 (Matthew Roughan): Signals and Images, Representations, Transformations and Linear Algebra
The goal of this section would be to create a deep understanding of what data really is, i.e., a representation of a signal, image or other measurement as a high-dimensional vector.
Representation requires a strong understanding of linear algebra, for instance how signals can be transformed into alternative representations.
Module 2 (Lewis Mitchell): Optimisation, Statistics and Regularisation
The goal of this section is to show that a vast amount of statistics and machine learning can be expressed as optimisation problems and that once this is understood, the underlying problem can often be altered to lead to more practical implementations.
Module 3 (Simon): Artificial Neural Networks and Machine Learning
The goal of this section is to bring together the threads into a deeper understanding of how neural networks really work, with examples from modern computer vision.
Outcomes:
1. Understand fundamentals of Machine Learning
2. Apply machine learning to a problem
3. Implementation of algorithms
4. Determine appropriate techniques to use in a particular setting
5. Derive new methods of machine learning appropriate to a task
6. Create workflows to support rigorous implementation machine learning tasksUniversity Graduate Attributes
This course will provide students with an opportunity to develop the Graduate Attribute(s) specified below:
University Graduate Attribute Course Learning Outcome(s) Attribute 1: Deep discipline knowledge and intellectual breadth
Graduates have comprehensive knowledge and understanding of their subject area, the ability to engage with different traditions of thought, and the ability to apply their knowledge in practice including in multi-disciplinary or multi-professional contexts.
all Attribute 2: Creative and critical thinking, and problem solving
Graduates are effective problems-solvers, able to apply critical, creative and evidence-based thinking to conceive innovative responses to future challenges.
all Attribute 3: Teamwork and communication skills
Graduates convey ideas and information effectively to a range of audiences for a variety of purposes and contribute in a positive and collaborative manner to achieving common goals.
1,5 Attribute 4: Professionalism and leadership readiness
Graduates engage in professional behaviour and have the potential to be entrepreneurial and take leadership roles in their chosen occupations or careers and communities.
all Attribute 5: Intercultural and ethical competency
Graduates are responsible and effective global citizens whose personal values and practices are consistent with their roles as responsible members of society.
all Attribute 8: Self-awareness and emotional intelligence
Graduates are self-aware and reflective; they are flexible and resilient and have the capacity to accept and give constructive feedback; they act with integrity and take responsibility for their actions.
all -
Learning Resources
Required Resources
All required materials will be provided.Recommended Resources
Course github:Â https://github.com/AdelaideUniversityMathSciences/MathsForAI
Deep Learning book:Â https://www.deeplearningbook.org
Deep learning course:Â https://deeplearningmath.org
Other useful online textbooks:
- https://udlbook.github.io/udlbook/
-Â https://d2l.ai/index.html
-Â https://probml.github.io/pml-book/book1.html
Online Learning
This course uses MyUni exclusively for providing electronic resources, such as lecture notes, assignment papers, and sample solutions. Students should make appropriate use of these resources. -
Learning & Teaching Activities
Learning & Teaching Modes
This course relies on combined lecture and tutorial classes as the primary learning mechanism for the material. A sequence of written and/or online assignments provides assessment opportunities for students to gauge their progress and understanding.Workload
The information below is provided as a guide to assist students in engaging appropriately with the course requirements.
The information below is provided as a guide to assist students in engaging appropriately with the course requirements.
Activity Quantity Workload Hours Lectures 30 90 Tutorials 6 18 Assignments 4 24 Project 1 24 Total 156 Learning Activities Summary
Lecture Outline- Basics
- Optimisation
- Signal processing
- Linear algebra
- Foundations of deep learning
- Neural networks
- Convolutional NNs
- Implementation aspects
- PyTorch
- Modern deep learning
- Attention mechanism
- Transformers
- Basics
-
Assessment
The University's policy on Assessment for Coursework Programs is based on the following four principles:
- Assessment must encourage and reinforce learning.
- Assessment must enable robust and fair judgements about student performance.
- Assessment practices must be fair and equitable to students and give them the opportunity to demonstrate what they have learned.
- Assessment must maintain academic standards.
Assessment Summary
Component Weighting Objective Assessed Assignments 40% all Project 50% all Competition 10% all
For details of on-going assessment refer to my-uni course.Assessment Related Requirements
An aggregate score of at least 50% is required to pass the course.Assessment Detail
There may be changes to these dates as the semester progresses.Assessment item Distributed (approx) Due date (approx) Weighting Assignment 1 Week 2 Week 4 10% Assignment 2 Week 4 Week 6 10% Assignment 3 Week 7 Week 9 10% Assignment 4 Week 9 Week 11 10% Project Week 6 Week 13 50% Competition Week 1 Week 13 10% Submission
Homework assignments must either be given to the lecturer in person or left in the box outside the lecturer's office by the given due time. Failure to meet the deadline without reasonable and verifiable excuse may result in a significant penalty for that assignment. The last day on which a miniproject may be submitted is the last teaching day of the semester.Course Grading
Grades for your performance in this course will be awarded in accordance with the following scheme:
M11 (Honours Mark Scheme) Grade Grade reflects following criteria for allocation of grade Reported on Official Transcript Fail A mark between 1-49 F Third Class A mark between 50-59 3 Second Class Div B A mark between 60-69 2B Second Class Div A A mark between 70-79 2A First Class A mark between 80-100 1 Result Pending An interim result RP Continuing Continuing CN Further details of the grades/results can be obtained from Examinations.
Grade Descriptors are available which provide a general guide to the standard of work that is expected at each grade level. More information at Assessment for Coursework Programs.
Final results for this course will be made available through Access Adelaide.
-
Student Feedback
The University places a high priority on approaches to learning and teaching that enhance the student experience. Feedback is sought from students in a variety of ways including on-going engagement with staff, the use of online discussion boards and the use of Student Experience of Learning and Teaching (SELT) surveys as well as GOS surveys and Program reviews.
SELTs are an important source of information to inform individual teaching practice, decisions about teaching duties, and course and program curriculum design. They enable the University to assess how effectively its learning environments and teaching practices facilitate student engagement and learning outcomes. Under the current SELT Policy (http://www.adelaide.edu.au/policies/101/) course SELTs are mandated and must be conducted at the conclusion of each term/semester/trimester for every course offering. Feedback on issues raised through course SELT surveys is made available to enrolled students through various resources (e.g. MyUni). In addition aggregated course SELT data is available.
-
Student Support
- Academic Integrity for Students
- Academic Support with Maths
- Academic Support with writing and study skills
- Careers Services
- International Student Support
- Library Services for Students
- LinkedIn Learning
- Student Life Counselling Support - Personal counselling for issues affecting study
- Students with a Disability - Alternative academic arrangements
- YouX Student Care - Advocacy, confidential counselling, welfare support and advice
-
Policies & Guidelines
This section contains links to relevant assessment-related policies and guidelines - all university policies.
- Academic Credit Arrangements Policy
- Academic Integrity Policy
- Academic Progress by Coursework Students Policy
- Assessment for Coursework Programs Policy
- Copyright Compliance Policy
- Coursework Academic Programs Policy
- Elder Conservatorium of Music Noise Management Plan
- Intellectual Property Policy
- IT Acceptable Use and Security Policy
- Modified Arrangements for Coursework Assessment Policy
- Reasonable Adjustments to Learning, Teaching & Assessment for Students with a Disability Policy
- Student Experience of Learning and Teaching Policy
- Student Grievance Resolution Process
-
Fraud Awareness
Students are reminded that in order to maintain the academic integrity of all programs and courses, the university has a zero-tolerance approach to students offering money or significant value goods or services to any staff member who is involved in their teaching or assessment. Students offering lecturers or tutors or professional staff anything more than a small token of appreciation is totally unacceptable, in any circumstances. Staff members are obliged to report all such incidents to their supervisor/manager, who will refer them for action under the university's student’s disciplinary procedures.
The University of Adelaide is committed to regular reviews of the courses and programs it offers to students. The University of Adelaide therefore reserves the right to discontinue or vary programs and courses without notice. Please read the important information contained in the disclaimer.
