SIT744 - Deep Learning
Unit details
| Year | 2027 unit information |
|---|---|
| Enrolment modes | Trimester 1: Burwood (Melbourne), Online Trimester 2: Burwood (Melbourne), Waurn Ponds (Geelong), Online Trimester 3: GIFT City Campus |
| Credit point(s) | 1 |
| EFTSL value | 0.125 |
| Unit chair | Trimester 1: Wei Luo Trimester 2: Bahareh Nakisa |
| Prerequisite | SIT720 or SIT742 |
| Corequisite | Nil |
| Incompatible with | SIT319 |
| Educator-facilitated (scheduled) learning activities - on-campus unit enrolment | 1 x 3 hour seminar per week, weekly meetings. |
| Educator-facilitated (scheduled) learning activities - online unit enrolment | Online independent and collaborative learning including 1 x 2 hour online seminar per week, weekly meetings. |
| Typical study commitment | Students will on average spend 150 hours over the teaching period undertaking the teaching, learning and assessment activities for this unit. |
| Supplementary information | GIFT City (India) offering is available to students enrolled at the GIFT City (India) campus only. |
Content
Deep learning is a disruptive technology for data science and artificial intelligence. This unit is for students to develop practical knowledge of deep learning and associated applications. Learning activities will focus on understanding deep learning theories, constructing deep learning models for handling structured and unstructured data, such as images, videos, and texts. Concepts such as computational graphs and representation learning that form core knowledge in this unit will be introduced. Students will also learn about deep learning techniques for data analytics such as convolutional networks, recurrent networks, and neural embedding methods which are being widely adopted in industries.
Learning outcomes
| ULO | These are the Unit Learning Outcomes (ULOs) for this unit. At the completion of this unit, successful students can: | Alignment to Deakin Graduate Learning Outcomes (GLOs) |
|---|---|---|
| ULO1 | Explain deep learning and its role in data science and AI. | GLO1: Discipline-specific knowledge and capabilities |
| ULO2 | Apply deep learning theory to formulate data analytics or artificial intelligence problems. | GLO1: Discipline-specific knowledge and capabilities |
| ULO3 | Design suitable deep learning algorithms for unsupervised learning and supervised learning problems. | GLO1: Discipline-specific knowledge and capabilities |
| ULO4 | Model and implement algorithms for processing structured and unstructured data, including images, videos, and texts, using industry-strength software frameworks. | GLO1: Discipline-specific knowledge and capabilities |
| ULO5 | Critically evaluate and extend existing deep learning approaches to design and justify innovative solutions for complex, ill-defined problems, integrating insights from contemporary research and demonstrating independent judgement under real-world constraints. | GLO1: Discipline-specific knowledge and capabilities |
Note - From 2026, Deakin will be transitioning to Graduate Attributes (GAs), which define the distinctive characteristics of a Deakin graduate. You may notice some units refer to Graduate Attributes (GAs) during this transition period.
Assessment
| Assessment Description | Student output | Grading and weighting (% total mark for unit) | Indicative due week |
|---|---|---|---|
| Learning portfolio | Learning portfolio consisting of quiz responses, problem-solving tasks, project work, code, and reports. | 100% | Week 12 |
The assessment due weeks provided may change. The Unit Chair will clarify the exact assessment requirements, including the due date, at the start of the teaching period.
Hurdle requirements
To be eligible to pass the unit, students must pass certain milestones in the Learning portfolio.
Learning resource
The texts and reading list for SIT744 can be found via the University Library.
Note: Select the relevant trimester reading list. Please note that a future teaching period's reading list may not be available until a month prior to the start of that teaching period so you may wish to use the relevant trimester's prior year reading list as a guide only.
Bring Your Own Device (BYOD)
To fully engage with Deakin's learning experiences, students must be able to access and use internet-connected devices as outlined in computing requirements at Deakin.
To support student success at Deakin, we have a bring-your-own-device (BYOD) learning environment that acknowledges that students and educators bring with them the digital tools they regularly use to complete academic tasks. These tools stay with you beyond the classroom, helping you to keep learning, explore ideas more deeply, and connect with knowledge in ways that matter to you.
Students requiring a loan device should visit our Loan Laptop webpage or students requiring longer-term assistance should visit our Student Financial Assistance webpage.
Unit fee information
Fees and charges vary depending on the type of fee place you hold, your course, your commencement year, the units you choose to study and their study discipline, and your study load.
Tuition fees increase at the beginning of each calendar year and all fees quoted are in Australian dollars ($AUD). Tuition fees do not include textbooks, computer equipment or software, other equipment or costs such as mandatory checks, travel and stationery.
For further information regarding tuition fees, other fees and charges, invoice due dates, withdrawal dates, payment methods visit our Current Students website.