Self-supervised feature learning for rapid processing of marine imagery. Fast and reliable quantitative estimates of marine environmental health are needed for scientific studies, design and management of protected areas, and regulatory compliance of industrial activity in the ocean. Australia is collecting seafloor images at increasing rates but expert annotations are not keeping up, meaning that typical machine learning approaches struggle. This project will develop self-supervised techniques ....Self-supervised feature learning for rapid processing of marine imagery. Fast and reliable quantitative estimates of marine environmental health are needed for scientific studies, design and management of protected areas, and regulatory compliance of industrial activity in the ocean. Australia is collecting seafloor images at increasing rates but expert annotations are not keeping up, meaning that typical machine learning approaches struggle. This project will develop self-supervised techniques that use large amounts of unlabeled data to enhance performance. Our design takes advantage of additional information available for marine imagery such as geolocation and remote sensing context. We will explore how these representations can guide additional sampling and improve performance in classification tasks.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
The Benefits of Utilising Visual-Spatial Representations of Numbers . The aim of this project is to investigate how visual-spatial representations of numbers enhance practice to promote the use of retrieval-based over counting-based strategies for children learning early arithmetic. About one-third of Australian children stay reliant on counting strategies for basic arithmetic, despite these being associated with lower achievement in mathematics in later years. Expected outcomes of this project ....The Benefits of Utilising Visual-Spatial Representations of Numbers . The aim of this project is to investigate how visual-spatial representations of numbers enhance practice to promote the use of retrieval-based over counting-based strategies for children learning early arithmetic. About one-third of Australian children stay reliant on counting strategies for basic arithmetic, despite these being associated with lower achievement in mathematics in later years. Expected outcomes of this project are new understandings of how problem-answer associations can be strengthened in memory and the development of tools to promote retrieval-based strategies. Potential benefits include children who are better prepared to take on higher-level mathematics in secondary school and, subsequently, more numerate citizens. Read moreRead less
Modelling complex learning spaces. The growing use of digital tools and resources means that students' learning activities are no longer tied to unique physical places. Their work is distributed across increasingly complex mixtures of physical and digital spaces, which both shape and are shaped by students' activity. This project aims to identify productive ways of modelling the characteristics and uses of complex learning spaces in higher education. Evidence and models generated by the project ....Modelling complex learning spaces. The growing use of digital tools and resources means that students' learning activities are no longer tied to unique physical places. Their work is distributed across increasingly complex mixtures of physical and digital spaces, which both shape and are shaped by students' activity. This project aims to identify productive ways of modelling the characteristics and uses of complex learning spaces in higher education. Evidence and models generated by the project aim to strengthen the logic connecting the use, management and design of learning spaces. A better understanding of the relations between pedagogy, activity and space will improve the work of architects and other designers, campus managers, university teachers and students themselves.Read moreRead less
Advanced Machine Learning with Bilevel Optimization. There is an urgent need to develop a new machine learning (ML) paradigm that can overcome data-privacy and model-size constraints in real-world applications. This project aims to develop an advanced paradigm of ML with bilevel optimisation, called bilevel ML. A theoretically-guaranteed fast approximate solver and a new fuzzy bilevel learning framework will be developed to achieve the aim in complex situations; a methodology to transfer knowled ....Advanced Machine Learning with Bilevel Optimization. There is an urgent need to develop a new machine learning (ML) paradigm that can overcome data-privacy and model-size constraints in real-world applications. This project aims to develop an advanced paradigm of ML with bilevel optimisation, called bilevel ML. A theoretically-guaranteed fast approximate solver and a new fuzzy bilevel learning framework will be developed to achieve the aim in complex situations; a methodology to transfer knowledge and an approach to fast-adapt bilevel optimization solutions when required computing resources change. The anticipated outcomes should significantly improve the reliability of ML with benefits for safety learning and computing resource optimisation in ML-based data analytics.Read moreRead less
Gendered engagement and participation in sciences and mathematics. This project aims to identify the reasons for the declining numbers of girls (and boys) studying sciences, technology, engineering and mathematics (STEM) subjects during secondary school. This project will conduct complementary longitudinal studies in Australia, in collaboration with leading international scholars, analysing declining motivations, especially for girls/women, to show how this predicts different STEM career choices ....Gendered engagement and participation in sciences and mathematics. This project aims to identify the reasons for the declining numbers of girls (and boys) studying sciences, technology, engineering and mathematics (STEM) subjects during secondary school. This project will conduct complementary longitudinal studies in Australia, in collaboration with leading international scholars, analysing declining motivations, especially for girls/women, to show how this predicts different STEM career choices and actual occupational outcomes, to yield theoretical developments and inform policy to improve the participation of girls/women (and boys/men) in these fields. Expected outcomes of this project include the provision of comprehensive evidence-informed recommendations to Federal and State government, industry and education stakeholders, which will enable the coordinated development of intervention programs to address these issues.Read moreRead less
Understanding Growth in Emotion Regulatory Flexibility in Emerging Adults. Emerging adults (ages 18-25) are now facing unparalleled social and technological change and the on-going effects of the COVID-19 pandemic. Such demands can be overwhelming and undermine engagement with education and employment, with serious impacts for the individual and society. At the same time, our novel model proposes that the diverse daily adult-like stressors that characterise emerging adulthood can also drive grow ....Understanding Growth in Emotion Regulatory Flexibility in Emerging Adults. Emerging adults (ages 18-25) are now facing unparalleled social and technological change and the on-going effects of the COVID-19 pandemic. Such demands can be overwhelming and undermine engagement with education and employment, with serious impacts for the individual and society. At the same time, our novel model proposes that the diverse daily adult-like stressors that characterise emerging adulthood can also drive growth in flexible emotion regulation when combined with reflection on, and insight into, their own coping processes. Our research expands scientific knowledge by taking the first steps to uncover why some emerging adults increase their ability to flexibly regulate their emotions over this period, whereas others fail to do so.Read moreRead less
Accelerated Finite-time Learning and Control in Cyber-Physical Systems. Efficient learning and control in cyber-physical systems such as smart grids and robotic systems are very important for achieving economic and social benefits. This project aims to establish a breakthrough accelerated finite-time dynamics theory and technology to assist in delivering efficient learning and control. Expected outcomes include new distributed accelerated finite-time dynamics based learning and control algorithm ....Accelerated Finite-time Learning and Control in Cyber-Physical Systems. Efficient learning and control in cyber-physical systems such as smart grids and robotic systems are very important for achieving economic and social benefits. This project aims to establish a breakthrough accelerated finite-time dynamics theory and technology to assist in delivering efficient learning and control. Expected outcomes include new distributed accelerated finite-time dynamics based learning and control algorithms and tools for optimal operations in cyber-physical systems. This should provide significant benefits including a practical technology for industry applications in smart grids and robotic systems, and training of the next generation engineers in this technology for Australia.Read moreRead less
Designing Learning Spaces for Diversity, Inclusion and Participation. This project aims to provide evidence-based guidance on how to design and/or modify mainstream schools to make it easier for students with disabilities to participate. It seeks to inform architects, educators, and policy makers about disabled students' spatial requirements and to develop strategies and tools to support the process of co-designing schools with people with lived experience of disability. The outcomes will includ ....Designing Learning Spaces for Diversity, Inclusion and Participation. This project aims to provide evidence-based guidance on how to design and/or modify mainstream schools to make it easier for students with disabilities to participate. It seeks to inform architects, educators, and policy makers about disabled students' spatial requirements and to develop strategies and tools to support the process of co-designing schools with people with lived experience of disability. The outcomes will include an inclusive learning spaces design framework. This is expected to benefit all students' access and meaningful involvement in learning through the development of more inclusive learning spaces. The research is significant because it integrates previously dissociated knowledge from architecture, education and health.Read moreRead less