Skip to main content

Honours and Masters project

Displaying 171 - 180 of 233 honours projects.


Primary supervisor: Russell Tsuchida

Pretrained models

The hidden layers of pretrained foundation models, such as ChatGPT, contain useful and abstract summaries of data. From an information-theoretic perspective, they might compress the data. From a machine learning perspective, they compute useful features of the data. From a statistics perspective, they might be sufficient statistics for a parameter of interest.

Probabilistic models

Primary supervisor: Waqar Hussain

Disruptive technologies such as artificial Intelligence (AI) systems can have unintended negative social and business consequences if not implemented with care. Specifically, faulty or biased AI applications may harm individuals, risk compliance and governance breaches, and damage to the corporate brand.

Primary supervisor: Guanliang Chen

Politeness plays a pivotal role in fostering constructive, respectful communication and maintaining positive social dynamics in educational settings. In online learning environments—such as discussion forums on Moodle—language becomes the primary medium for interaction between instructors and students. While prior studies have highlighted the benefits of politeness in building rapport and encouraging engagement, limited empirical work has systematically examined how politeness is expressed by both instructors and students in these digital spaces.

Primary supervisor: Vincent Lee

Issues and solutions exist on different aspects of the management of real-time data, such as persistence, visualisation, and online processing. This project is a research project to identify the significant issues of real-time data management in structural health monitoring (SHM), particularly for bridges, and implement an integrated software solution for enterprise usage. This project involves time series database design, visualisation and online processing of time series, and service-oriented and web-based software development.

Primary supervisor: Mor Vered

Goal recognition is defined as the problem of determining an agent’s intent from observations of its behaviour. Current research in goal recognition has focused on observing agents that are trying to achieve their goals in a rational manner. Other research has focused on observing agents that are deliberately trying to trick an observer into believing they are pursuing alternative goals to the ones they are actually pursuing. However there is also a need to recognise when a behaviour is suspicious, regardless of the goal that is being tried to be achieved.

Primary supervisor: Levin Kuhlmann

Background and motivation

As intelligent agents make decisions, any project aiming to realize human-like AGI should model decision-making.  As we have been pursuing the WBA approach to create AGI by learning from the architecture of the entire brain, we request you to model the decision-making of the mammalian brain.

Primary supervisor: Terrence Mak

Which route is the best to drive from Monash University (Clayton campus) to Melbourne CBD? 

For many of us, answering this question would likely mean opening a route natvigation app and asking the provider to give us the fastest route. For some of us, this question might not need to be answered as you may already be experienced to drive from Monash Uni to CBD, or simply find that the route computed by the app is insufficent to handle your specific requirements, preferences, or constraints. 

Primary supervisor: Russell Tsuchida

What is a mixture model?

You may have learned about mixture models in a machine learning or statistics course. A mixture model with K component densities is defined by

  • a set of K nonnegative mixture weights summing to one, and
  • a corresponding set of K nonnegative component densities, each of which integrates to one.

The sum of the product of the mixture weights and component densities is guaranteed to be nonnegative and integrates to one, meaning it is a valid probability density.

Primary supervisor: Shujie Cui

Verifiable Dynamic Searchable Symmetric Encryption (VDSSE) enables users to securely outsource databases (document sets) to cloud servers and perform searches and updates. The verifiability property prevents users from accepting incorrect search results returned by a malicious server. However, the community currently only focuses on preventing malicious behavior from the server but ignores incorrect updates from the client, which are very likely to happen in multi-user settings. Indeed most existing VDSSE schemes are not sufficient to tolerate incorrect updates from users. For instance,…

Primary supervisor: Ron Steinfeld

Since the 1990s, researchers have known that commonly-used public-key cryptosystems (such as RSA and Diffie-Hellman systems) could be potentially broken using efficient algorithms running on a special type of computer based on the principles of quantum mechanics, known as a quantum computer. Due to significant recent advances in quantum computing technology, this threat may become a practical reality in the coming years. To mitigate against this threat, new `quantum-safe’ (a.k.a.