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. 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.

24/9/19: Admin - updating the exam duration to include additional 10 minutes as per University requirement.

Upon successful completion of this unit students should be able to:

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

020399

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 and 10 minutes): 40%; In-semester assessment: 60%

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

One of (FIT2086, FIT3154, FIT3080) and one of (FIT1045, FIT1053)

Basic knowledge in linear algebra (up to Singular Value Decomposition), basic knowledge in supervised and unsupervised learning, fundamentals of machine learning is a bonus (but not a must), familiarity with Python programming, Jupyter Notebook. Previous encounters with deep learning framework (e.g., Tensorflow) is an advantage, but not mandatory.