Generative Visual Pre-training on Unlabelled Big Data. This project aims to develop a generative visual pre-training of large-scale deep neural networks on unlabelled big data. Developing pre-trained visual models that are accurate, robust, and efficient for downstream tasks is a keystone of modern computer vision, but it poses challenges and knowledge gaps to existing unsupervised representation learning. Expected outcomes include new theories and algorithms for unsupervised visual pre-training ....Generative Visual Pre-training on Unlabelled Big Data. This project aims to develop a generative visual pre-training of large-scale deep neural networks on unlabelled big data. Developing pre-trained visual models that are accurate, robust, and efficient for downstream tasks is a keystone of modern computer vision, but it poses challenges and knowledge gaps to existing unsupervised representation learning. Expected outcomes include new theories and algorithms for unsupervised visual pre-training, which are anticipated to deepen our understanding of visual representation and make it easier to build and deploy computer vision applications and services. Examples of benefits include modernising machines in manufacturing and farming with visual intelligence. Read moreRead less
Exploiting Geometries of Learning for Fast, Adaptive and Robust AI. This project aims to uniquely exploit geometric manifolds in deep learning to advance the frontier of Artificial Intelligence (AI) research and applications in cybersecurity and general cognitive tasks. It expects to develop new theories, algorithms, tools, and technologies for machine learning systems that are fast, adaptive, lifelong and robust, even with limited supervision. Expected outcomes will enhance Australia's capabili ....Exploiting Geometries of Learning for Fast, Adaptive and Robust AI. This project aims to uniquely exploit geometric manifolds in deep learning to advance the frontier of Artificial Intelligence (AI) research and applications in cybersecurity and general cognitive tasks. It expects to develop new theories, algorithms, tools, and technologies for machine learning systems that are fast, adaptive, lifelong and robust, even with limited supervision. Expected outcomes will enhance Australia's capability and competitiveness in AI, and deliver robust and trustworthy learning technology. The project should provide significant benefits not only in advancing scientific and translational knowledge but also in accelerating AI innovations, safeguarding cyberspace, and reducing the burden on defence expenses in Australia.Read moreRead less
Processing mathematics tasks: the nature and role of visual and non-visual reasoning in digital and non-digital environments. Within the next four years, it is likely that the National Assessment Plan for Literacy and Numeracy (NAPLAN) will be administered in a digital mode. This project identifies differences between the delivery of mathematics assessment in pencil-and-paper and computer-based modes. Primary students' mathematics reasoning is compared across these modes and to cohorts from Sing ....Processing mathematics tasks: the nature and role of visual and non-visual reasoning in digital and non-digital environments. Within the next four years, it is likely that the National Assessment Plan for Literacy and Numeracy (NAPLAN) will be administered in a digital mode. This project identifies differences between the delivery of mathematics assessment in pencil-and-paper and computer-based modes. Primary students' mathematics reasoning is compared across these modes and to cohorts from Singapore.Read moreRead less
David and Goliath - what planets can do to the stars that created them. We used to think that when stars expand during their old age, they would destroy all their close-by planets. Today we know that if a star swallows a Jupiter-like planet it can suffer indigestion. The project will study how star-planet interactions takes place, determine their impact on the lives of stars and glimpse at the future of our own solar system.
Towards efficient real-time generation of detectable musical macrostructure. Efficient generation of detectable large scale musical structure is needed for commercial audiovisual applications, and for creative music making. But computer mediation of music has focused elsewhere: on sound synthesis and sequencing, editing, mixing and notation. I will apply computational processes like the handling of chunks of genetic information in evolution, to generate large scale musical structure. I will con ....Towards efficient real-time generation of detectable musical macrostructure. Efficient generation of detectable large scale musical structure is needed for commercial audiovisual applications, and for creative music making. But computer mediation of music has focused elsewhere: on sound synthesis and sequencing, editing, mixing and notation. I will apply computational processes like the handling of chunks of genetic information in evolution, to generate large scale musical structure. I will control segmentation; framing of internal segments; spatialisation; and the overlaying of separable musical streams. Expert cognitive assessment of the resultant structures will be investigated, and theories of segmentation, streaming and their relationships with expression and affect developed and tested.Read moreRead less
Historical frontier violence: drivers, legacy and the role of truth-telling. This project aims to build data to identify the historical factors that incited frontier violence; quantify the legacy on communities today and conduct fieldwork to understand how historical trauma is transmitted across generations. This project expects to develop new knowledge on the circumstances and legacy of settlement and the origins of gaps in life prospects between Indigenous and non-Indigenous Australians. Our e ....Historical frontier violence: drivers, legacy and the role of truth-telling. This project aims to build data to identify the historical factors that incited frontier violence; quantify the legacy on communities today and conduct fieldwork to understand how historical trauma is transmitted across generations. This project expects to develop new knowledge on the circumstances and legacy of settlement and the origins of gaps in life prospects between Indigenous and non-Indigenous Australians. Our expectation is that this will increase public acceptance of the circumstances of settlement and the need to make amends. This project should help increase public support for truth-telling and better relations between Indigenous and non-Indigenous Australians, a vital step towards reconciliation and healing the nation. Read moreRead less
A longitudinal study of the interaction of home and school language in three Aboriginal communities. The importance of language skills cannot be underestimated, and contribute to 'a healthy start to life'. In multilingual Indigenous communities, children must negotiate the complexities of different languages used for different purposes. This project will provide detailed insights into how children manage differences between home and school language, the kinds of problems they encounter when the ....A longitudinal study of the interaction of home and school language in three Aboriginal communities. The importance of language skills cannot be underestimated, and contribute to 'a healthy start to life'. In multilingual Indigenous communities, children must negotiate the complexities of different languages used for different purposes. This project will provide detailed insights into how children manage differences between home and school language, the kinds of problems they encounter when they enter the school system, and how their languages develop over the first four crucial years of school which provide the foundation for the children's future education. Their ability to manage the language of school underpins their ability to lead successful and engaged lives as adults. Read moreRead less