Research Areas
Research areas in Machine Learning
Monash conducts world-class research and industries choose to partner and connect with us to build lasting AI-based systems that serve community, society and address world problems.
Our research covers six key areas within the Faculty of IT and integrates seamlessly with other faculties and disciplines.
Explore these research areas available within the Machine Learning group

Bayesian and Statistical Machine Learning
The core theory of machine learning is statistical and Bayesian computation, regardless of whether one is using deep learning or predictive analytics. We develop computational techniques with a statistical basis to handle complex knowledge structures, process large scale data, and harness available prior knowledge, demanded of modern artificial intelligence applications.

Deep Learning
Deep learning (DL) is a prominent and fast-growing area of machine learning driving unprecedented progress in modern artificial intelligence (AI) systems. It develops autonomous, self-teaching systems that analyse many layers of data variables.

Natural Language Analytics
Large proportions of data in the modern world are text: email, social media, nursing notes, news and reports. Moreover, the text comes in a complex context: users, time, medical classification hierarchies, etc. Our analytics work uses the latest Bayesian and deep learning methods to address key problems in a variety of domain contexts.

Relational and Structured Learning
Social networks which record interactions in time, gene regulatory networks, and multi-relation health records all go way beyond traditional tabular data that machine learning and statistics were originally developed with. Our work develops representations and algorithms for the analysis of these valued data types.

Online Learning and Learning from Non-stationary Distributions
We live in a world that is perpetually changing but Data Analytics often considers that the problem under study is stable. Our work studies non-stationary distributions and how to build algorithms that can learn if the problem is changing over time.

Time Series Analytics
Time series are now ubiquitous and their analysis is an exciting field of research. Applications we work on include: working out if an insect flying through a sensor is a vector of the Nile virus, understanding if an area imaged by satellite images is prone to fire, or activity recognition from the accelerometers in your smartphone.