FIT3181 - Deep learning - 2019

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.

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.

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

Minimum total expected workload equals 12 hours per week comprising:

1. Contact hours:
   • Two hours lectures
   • Two hours laboratories
2. Additional requirements (all students):
   • A minimum of 8 hours per week of personal study for completing lab/tutorial activities, assignments, private study and revision.

See also Unit timetable information

Data Science