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
Discovery Early Career Researcher Award - Grant ID: DE240100144
Funder
Australian Research Council
Funding Amount
$444,447.00
Summary
Universal Model Selection Criteria for Scientific Machine Learning. This project aims to develop provably reliable universal model selection criteria to facilitate trustworthy scientific machine learning. Combining stochastic methods with an innovative geometric approach to basic statistical principles, this project expects to characterise, combine, and refine the most successful heuristics for designing and training huge models, such as deep neural networks, into a cohesive theoretical framewor ....Universal Model Selection Criteria for Scientific Machine Learning. This project aims to develop provably reliable universal model selection criteria to facilitate trustworthy scientific machine learning. Combining stochastic methods with an innovative geometric approach to basic statistical principles, this project expects to characterise, combine, and refine the most successful heuristics for designing and training huge models, such as deep neural networks, into a cohesive theoretical framework. The expected outcomes include a general toolkit for assisting neural network design at the forefront of scientific applications. This should significantly improve the quality of scientific predictions by facilitating confident adoption of deep learning methods into the pantheon of trustworthy modeling techniques. 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
Using cognitive models to understand memorability of real world images. This proposal aims to understand and make predictions about which real world images -- specifically living things, objects, and human faces -- that people will remember remember via an integration of cognitive models of memory and machine learning techniques. Computer vision models and similarity scaling techniques will be used to produce psychological representations of the images. These representations will then be integra ....Using cognitive models to understand memorability of real world images. This proposal aims to understand and make predictions about which real world images -- specifically living things, objects, and human faces -- that people will remember remember via an integration of cognitive models of memory and machine learning techniques. Computer vision models and similarity scaling techniques will be used to produce psychological representations of the images. These representations will then be integrated with cognitive models of memory, which predict that images are more likely to be recognized if they are similar to each of the representations in memory. Large scale memory and similarity rating datasets will be used to develop and test the model.Read moreRead less
Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models ....Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models, based on the incorporation of an explicit searchable memory, which will dramatically reduce model size, hardware requirements and energy usage. This will make modern natural language processing more accessible, while also providing greater flexibility, allowing for more adaptable and portable technologies.Read moreRead less
Structural And Functional Studies On The Interaction Between Alpha2-Antiplasmin And Plasmin
Funder
National Health and Medical Research Council
Funding Amount
$280,400.00
Summary
Fibrinolysis is the process by which the body dissolves clots. In this proposal we aim to investigate how the fibrinolysis inhibitor alpha2-antiplasmin interacts with the clot dissolving protease enzyme plasmin. These data will be useful for developing new approaches to accelerate plasmin-mediated clot breakdown.
Discovery Early Career Researcher Award - Grant ID: DE240101089
Funder
Australian Research Council
Funding Amount
$436,847.00
Summary
Trustworthy Hypothesis Transfer Learning. It is urgent to develop a new hypothesis transfer learning scheme that can overcome potential risks when finetuning unreliable large-scale pre-trained models. This project aims to develop an advanced and reliable scheme of hypothesis transfer learning, called Trustworthy Hypothesis Transfer Learning (TrustHTL). A new theoretically guaranteed heterogeneous hypothesis transfer learning framework will be developed to handle heterogeneous situations; a metho ....Trustworthy Hypothesis Transfer Learning. It is urgent to develop a new hypothesis transfer learning scheme that can overcome potential risks when finetuning unreliable large-scale pre-trained models. This project aims to develop an advanced and reliable scheme of hypothesis transfer learning, called Trustworthy Hypothesis Transfer Learning (TrustHTL). A new theoretically guaranteed heterogeneous hypothesis transfer learning framework will be developed to handle heterogeneous situations; a methodology to disinherit risks of pre-trained models and a new fuzzy relation based distributional discrepancy in heterogeneous transfer learning scenarios. The outcomes should significantly improve the reliability of machine learning with benefits for safety learning in data analytics.Read moreRead less
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
Discovery Early Career Researcher Award - Grant ID: DE140100751
Funder
Australian Research Council
Funding Amount
$379,506.00
Summary
How health shapes young children’s academic outcomes, and opportunities to intervene. Every year, about 280,000 Australian children make the crucial transition from preschool to formal education. Within this population, there is a wide range of learning capabilities and levels of preparedness. Children who have difficulties during the early years have greater risk of poorer academic and social outcomes. This project aims to determine how children's academic outcomes are shaped by common physical ....How health shapes young children’s academic outcomes, and opportunities to intervene. Every year, about 280,000 Australian children make the crucial transition from preschool to formal education. Within this population, there is a wide range of learning capabilities and levels of preparedness. Children who have difficulties during the early years have greater risk of poorer academic and social outcomes. This project aims to determine how children's academic outcomes are shaped by common physical health problems during the early years of school and how best to address these problems within the traditional school setting. This will inform future research as to the opportunities to help all children have the best opportunity to learn so they can reach their academic potential.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