This unit will be a core elective in the Master of Artificial Intelligence to be introduced in 2020.

Deep learning (DL) has become increasingly important in modern machine learning and AI systems. The job market and industry constantly look for skills in DL. The fundamental knowledge of DL arguably becomes the core knowledge in data science (DS), machine learning and AI. At Monash, this topic has been touched upon only scarcely across some DS units. Moreover, there is currently NO deep learning unit being offered at the graduate level. The proposal of this new unit is to address this situation and to offer a unified deep learning unit to students, bridging the important knowledge and skill gap in this fast- growing area, in particularly for graduate students.

11/11/2019: Removing FIT5201 from prerequisite units, and removing the prerequisite knowledge statement. Entry into C6007 and the core units FIT5047 and FIT5197 cover the required knowledge. Effective 2020.

18/09/2020 - Admin: Update to include new assessment and teaching approach fields as per Handbook requirements.

29/09/2021 - Admin: Update to assessment to include both Semester 2 and Term 3 information.

17/03/2021 - Admin: Adding Reasons for Change - change to prerequisites and corequisites as per email discussion with DDE.

At the completion of this unit, students should be able to:

1. Describe the life cycle of a machine leaning system, what is involved in designing such systems and strategy to maintain them.
2. Describe what deep learning (DL) is, access what makes DL work or fail and where they should be applied.
3. Develop and apply deep neural networks, convolutional neural networks, recurrent neural networks and different optimization strategies for training them.
4. Develop unsupervised feature learning models and representation learning models.

020119 Artificial Intelligence

Modern machine learning provides core underlying theory and techniques to data science and artificial intelligence. This unit is for students to develop practical knowledge of modern machine learning and deep learning and how they can be used in real-world settings such as image recognition or text clustering via neural embeddings. Learning activities will focus on designing machine learning systems, a broad landscape of supervised and unsupervised learning methods with a focus on modern deep learning knowledge for data analytics including deep neural networks, representation learning and embedding methods, and deep models used for time-series data which are rapidly used in science and industry.

On-campus

Examination (2 hours): 40%; In-semester assessment: 60%

Semester

1. Assignment 1 - 20% - ULO: ?
2. In-semester test 1 - 10% - ULO: ?
3. In-semester test 2 - 10% - ULO: ?
4. Assignment 2 - 20% - ULO: ?
5. Examination - 40% - ULO: ?

Term 3

1. Assessment 1a - 20% - ULO: 1, 2
2. Assessment 1b - 20% - ULO: 3, 4
3. Assessment 2 - 20% - ULO: 1, 2, 3, 4
4. Final exam - 40% - ULO: 1, 2, 3, 4

6

Minimum total expected workload equals 12 hours per week comprising:

• Two hours/week lectures
• Two hours/week laboratories

A minimum of 8 hours per week of personal study for completing lab/tutorial activities, assignments, private study and revision

FIT

FIT9133 or FIT9136