A novel and efficient approach for optimisation involving iterative solvers. Computationally expensive simulations involving iterative solvers are increasingly being used in industry to assess performance of products and processes. Repeated use of such simulations is necessary to identify optimum solutions. Even with today's computing power, many such tasks remain computationally prohibitive. This project presents a novel approach to solve optimisation problems involving iterative solvers with l ....A novel and efficient approach for optimisation involving iterative solvers. Computationally expensive simulations involving iterative solvers are increasingly being used in industry to assess performance of products and processes. Repeated use of such simulations is necessary to identify optimum solutions. Even with today's computing power, many such tasks remain computationally prohibitive. This project presents a novel approach to solve optimisation problems involving iterative solvers with limited computing budget. A wide range of industries involved in product and process design would gain a significant competitive advantage from this unique technical innovation. In addition, this technology will be invaluable to uncover and understand complex natural phenomena.Read moreRead less
Learning deep resilient behaviour for uncertainty-aware autonomy. This research project aims to propose a novel framework for developing uncertainty-aware autonomous systems using deep learning. There are fundamental gaps in our knowledge of deep uncertainty quantification and its application for risk-aware decision making. Novel algorithms will be proposed to reliably generate deep uncertainty estimates with low computational overhead. These estimates will be then exploited by safety-critical s ....Learning deep resilient behaviour for uncertainty-aware autonomy. This research project aims to propose a novel framework for developing uncertainty-aware autonomous systems using deep learning. There are fundamental gaps in our knowledge of deep uncertainty quantification and its application for risk-aware decision making. Novel algorithms will be proposed to reliably generate deep uncertainty estimates with low computational overhead. These estimates will be then exploited by safety-critical systems such as autonomous robots to identify risky actions and avoid catastrophise. Developed algorithms will be implemented on an autonomous robotic system to make it averse to uncertainties. The outcomes will greatly increase reliable telerobotic applications in mining, manufacturing, defence, and health.Read moreRead less
The neural dynamics of real-time processing in the brain. The aim of this project is to investigate a new model for predictive coding of sensory processing in the brain in which the brain compensates for the time delays in neural transmission by maintaining a real-time temporal alignment of the neural activity. This results in a representation of sensory information that is aligned in time across the cortex, offering a new fundamental principle for how the brain functions in a highly dynamic wor ....The neural dynamics of real-time processing in the brain. The aim of this project is to investigate a new model for predictive coding of sensory processing in the brain in which the brain compensates for the time delays in neural transmission by maintaining a real-time temporal alignment of the neural activity. This results in a representation of sensory information that is aligned in time across the cortex, offering a new fundamental principle for how the brain functions in a highly dynamic world whose outcomes would provide a deeper understanding of brain function. It could also have profound significance for artificial intelligence and brain-inspired technologies, as well as benefit neural sensory prostheses and brain-machine interfaces.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE210101623
Funder
Australian Research Council
Funding Amount
$456,450.00
Summary
High-Fidelity Motion Simulator using Sickness-Free Motion Cueing Algorithm. This project aims to address the key deficiencies of driving and flight simulators by developing novel human perception-based motion cueing algorithms (MCAs) and leveraging advanced artificial intelligence techniques. Despite widespread applications, existing motion simulators fail to deliver the most accurate human sensation to the user. This failure is mainly attributable to the inefficiency and inflexibility of MCAs u ....High-Fidelity Motion Simulator using Sickness-Free Motion Cueing Algorithm. This project aims to address the key deficiencies of driving and flight simulators by developing novel human perception-based motion cueing algorithms (MCAs) and leveraging advanced artificial intelligence techniques. Despite widespread applications, existing motion simulators fail to deliver the most accurate human sensation to the user. This failure is mainly attributable to the inefficiency and inflexibility of MCAs used by simulators. It is expected that this project will significantly increase simulator motion fidelity and eliminate motion sickness. This will have substantial benefits to Australian research communities and industries, particularly where simulators are used for training, performance evaluation and virtual prototyping.Read moreRead less
Modelling and manipulating brain network dynamics across the lifespan. This project aims to integrate advanced computational modelling and state-of-the-art recording techniques to generate new knowledge on the neural basis of ageing. People are said to grow wiser as they grow older, though more likely they will experience cognitive slowing and reduced memory functions that interfere with their daily lives. The anticipated goal of the project is to develop techniques to predict the personalised e ....Modelling and manipulating brain network dynamics across the lifespan. This project aims to integrate advanced computational modelling and state-of-the-art recording techniques to generate new knowledge on the neural basis of ageing. People are said to grow wiser as they grow older, though more likely they will experience cognitive slowing and reduced memory functions that interfere with their daily lives. The anticipated goal of the project is to develop techniques to predict the personalised effects of brain stimulation on the ageing brain. The outcomes of this research could significantly improve understanding of brain ageing, and advance the fields of systems neuroscience, network science, and brain stimulation.Read moreRead less
Quantification, optimisation, and application of deep uncertainty. This project aims to develop a framework for deep uncertainty quantification. There is currently a fundamental gap between deep learning research and the methods required to quantify and manage uncertainties. The research will propose a novel distribution-free methodology to generate deep predictive uncertainty estimates to avoid the assumptions of existing methods. The quality of estimates will be enhanced by applying an interva ....Quantification, optimisation, and application of deep uncertainty. This project aims to develop a framework for deep uncertainty quantification. There is currently a fundamental gap between deep learning research and the methods required to quantify and manage uncertainties. The research will propose a novel distribution-free methodology to generate deep predictive uncertainty estimates to avoid the assumptions of existing methods. The quality of estimates will be enhanced by applying an interval-based adversarial training step. The project is expected to help data-driven Australian organisations and industries to better quantify and manage forecasting uncertainties. This project will provide them with significant cost savings through better decision making and more robust planning.Read moreRead less
Improving Legal Frameworks to Support Online Child Sex Abuse Prosecutions. This project aims to gain a deeper understanding of the nature and extent of online child sexual abuse prosecutions in Australia. Using empirical studies to draw on the practical experience of law enforcement and other stakeholders, it will generate new knowledge concerning the suitability of Australia's legal and policy frameworks to effectively investigate and prosecute such offences, with a particular focus on the Asia ....Improving Legal Frameworks to Support Online Child Sex Abuse Prosecutions. This project aims to gain a deeper understanding of the nature and extent of online child sexual abuse prosecutions in Australia. Using empirical studies to draw on the practical experience of law enforcement and other stakeholders, it will generate new knowledge concerning the suitability of Australia's legal and policy frameworks to effectively investigate and prosecute such offences, with a particular focus on the Asia-Pacific region and the use of new technologies. Expected outcomes include evidence-based recommendations on criminal law reform and enforcement policy that aim to improve the international enforcement of online child sexual abuse offences, and to provide a model for other forms of serious transnational online crime.Read moreRead less
Democratisation of Deep Learning: Neural Architecture Search at Low Cost. The need to manually design Deep Learning-based Neural Networks (DNNs) limits their usage to AI experts and hinders the exploitation of their true potential more broadly, e.g., in farming, humanities. We aim to replace this tedious process through novel AI methods capable of generating DNNs that can perform significantly better and at a lower computational cost than manually designed DNNs. We further expand this idea to so ....Democratisation of Deep Learning: Neural Architecture Search at Low Cost. The need to manually design Deep Learning-based Neural Networks (DNNs) limits their usage to AI experts and hinders the exploitation of their true potential more broadly, e.g., in farming, humanities. We aim to replace this tedious process through novel AI methods capable of generating DNNs that can perform significantly better and at a lower computational cost than manually designed DNNs. We further expand this idea to solve complex real-world problems with both labelled and unlabelled data found in various applications including energy and climate change. The expected outcomes include the novel AI methods, highly trained AI researchers and a number of critical applications that will bring significant benefits to Australia and the world.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE200101708
Funder
Australian Research Council
Funding Amount
$406,821.00
Summary
New directions for using brain stimulation to understand brain function. Neuroplasticity is of fundamental importance to brain function as it mediates learning, memory and development. Deficits in neuroplasticity are observed in a number of neurological conditions and thought to contribute to cognitive dysfunction. This study is designed to develop a better understanding of the neurochemical and genetic factors impacting on neuroplasticity. In addition, it aims to (i) upregulate brain connectivi ....New directions for using brain stimulation to understand brain function. Neuroplasticity is of fundamental importance to brain function as it mediates learning, memory and development. Deficits in neuroplasticity are observed in a number of neurological conditions and thought to contribute to cognitive dysfunction. This study is designed to develop a better understanding of the neurochemical and genetic factors impacting on neuroplasticity. In addition, it aims to (i) upregulate brain connectivity in a precise and targeted manner, (ii) elicit functional increases in cognitive performance and (iii) demonstrate the relationship between functional connectivity and cognition. Outcomes include a better understanding of plasticity in the brain & a enhanced capacity to examine and modulate brain plasticity.Read moreRead less