Honours and Minor Thesis projects

Mini-CP https://www.info.ucl.ac.be/~pschaus/minicp.html is a minimal form of constraint programming solver, designed to allow for easy experimentation and learning. 

One of the most efficient approaches to discrete optimisation solving is using lazy clause generation, which is a hybrid SAT/CP approach to solving problems.  But MiniCP does not currently support this. 

Given a knowledge base describing the existing background constraints and assumptions about what is possible in the world as well as the prior experience of an autonomous agent on the one hand and probabilistic perception of the current state of the world of the autonomous agent, on the other hand, it is essential to devise and efficiently enumerate the most consistent world models that are likely to be valid under the prior knowledge in order to refine the agent’s up-to-date perception and take the most suitable actions.…

Building a robust and trustworthy (semi-)autonomous agent requires us to build a consistent picture of the state of the world based on the data received from some perception module.

In this project, you will build an autonomous agent in the MineRL environment for playing Minecraft or an agent for Animal-AI.  Herein, you will learn how to incorporate symbolic prior knowledge for improving the performance of an agent trained by using deep reinforcement learning (RL) technique, which is the core technique to build AlphaGo.

(This is *not* a minor thesis or honours project, but a summer scholarship project advert only available to existing Monash taught students).

This project provides an opportunity to build on an existing funded project that focussed on document annotation using a web platform. The idea of this project is to build systems that can help humans add labels to documents more rapidly. 

Android is a mobile operating system that occupies 72.11% market share globally. As the most popular mobile operating system, the android mobile app industry has been active for over a decade, generating billions of dollars in revenue for Google and thousands of mobile app developers. Several third-party Android app stores in China are estimated to generate over $8 billion in yearly revenue. Meanwhile, the number of bugs and vulnerabilities in mobile apps is growing. In 2016, 24.7% of mobile apps contained at least one high-risk security flaw.

The existing deep learning-based time series classification (TSC) algorithms have some success in multivariate time series, their accuracy is not high when we apply them to brain EEG time series (65-70%). This is because there is a large variation between EEG data of different subjects, so a TSC model cannot generalise on unseen subjects well. In this research project, we investigate self-supervised contrastive learning to encode the EEG data. This way we can better model the distribution of our EEG data before classifying it into different mental statuses. See recent work here [1].

Turning Point’s National Ambulance Surveillance System is a surveillance database comprising enriched ambulance clinical data relating to alcohol and other substance use, suicidal and self-injurious thoughts and behaviours, and mental health-related harms in the Australian population. These data are used to inform policy and intervention design and are the subject of ever-increasing demand from academic professionals and units, government departments, and non-government organisations.

Develop, implement, and test deep learning techniques for automatic classification of epileptic seizures using video data of seizures

This project takes a different approach to RL, inspired by evidence that Hippocampus replays to the frontal cortex directly. It is likely used for model building, as opposed to the mainstream view in cognitive science and ML - where 'experience replay' ultimately improves policy. The predicted benefits are sample efficiency, better ability to generalize to new tasks and an ability to learn new tasks without forgetting old ones.