Skip to main content

Self-aware neural networks

Primary supervisor

Levin Kuhlmann

This project is similar in flavour to the Conscious AI project but rather than come from a Philosophical/Neuroscience/Math/Theory angle, this project aims to build self-aware neural networks that are constructed in a way that is inspired by what we know about self-awareness circuits in the brain and the field of self-aware computing. The project will advanced state of the art AI for NLP or vision or both and embed self-awareness modules within these systems. This will likely involve a combination of the standard methods in these systems, such as transformer or diffusion networks and reinforcement learning to guide the self-aware learning and network formation. As such this expected to be a purely mathematical and computational project. 

To do this project you would need to apply for a Monash Scholarship.

Required knowledge

A decent theoretical background in physics, computer science, mathematics, engineering, neuroscience or psychology. 

Project funding

Other

Learn more about minimum entry requirements.