Deep Learning Analytics

Deep Learning Analytics is available as a postgraduate-level subject offered by the International College of Management, Sydney (ICMS). Please click the button below to find a postgraduate course.

Subject Code:

DAT804A

Subject Type:

Specialisation 

Subject Level:

800

Pre-requsite:

• DAT801A Big Data Architecture and Management 
• Course level study pre-requisite: a total of 16 credit points (4 subjects) prior to enrolling into the subject 

Credit Points:

4 credit points

Subject Aim:

Intelligent IT systems that offer artificial intelligence capabilities often rely on machine learning (ML). Deep Learning (DL) is a ML concept based on artificial neural networks that can learn to represent very complex patterns on vast amounts of data. For many applications, DL models outperform shallow ML models and traditional data analysis approaches, providing efficiency advances over business competitors by potentially supporting both, humans and other systems. Against this background, in some application areas it is crucial to develop skills in DL design, implementation and management in order to stay competitive by fully leveraging the potential business value of large and complex datasets.

In this subject, students will be introduced to the underlying key concepts and challenges of DL. It covers the features that distinguish DL from other ML or traditional data analytics techniques and provides a framework for the design, implementation, and evaluation of DL models.

Students will learn the foundation of neural networks (NNs) and will explore the main algorithms and concepts in DL such as backpropagation, convolutional NNs, and recurrent NNs. Based on that, students will be able to discern the type of problems that can be addressed via DL algorithms and identify the appropriate DL techniques to address them. Furthermore, students will become familiar with the practical information security risks of DL algorithms, be able to assess the risk of these, and develop appropriate countermeasures.

Learning Outcomes:

a) Critically reflect on and apply the knowledge of neural networks, the main algorithms and concepts of deep learning (DL) as contextualised to specific business scenarios and effectively communicate DL solutions to specialist and non-specialist audiences.

b) Critically analyse the use case environment, formulate deep learning design requirements, identify appropriate deep learning techniques to operationalise them, and justify decisions comprehensibly.

c) Critically evaluate risks and potentials of deep learning techniques and adapt them to complex business problems and regulatory environments.

d) Implement deep learning techniques to solve complex business problems and orchestrate them as a runnable prototype using distributed computing technologies.

e) Interpret and evaluate deep learning outcome/configurations and take targeted actions to adjust the outcome and its value provided to the problem solution.

Assessment Information:

Learning outcomes for this subject are assessed using a range of assessment tasks as described in the table below.

Broad topics to be covered: 

Please note that these topics are often refined and subject to change so for up to date weekly topics and suggested reading resources, please refer to the Moodle subject page.