Discovery Early Career Researcher Award - Grant ID: DE240100967
Funder
Australian Research Council
Funding Amount
$366,000.00
Summary
Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected o ....Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected outcomes include new paradigms for algorithm design and evaluation, and establishing the problem as a focus of international research. The key practical benefit would be to accelerate the wider deployment of visual perception in applications such as autonomous vehicles, interactive robotics, and video analysis.Read moreRead less
Using lasers to prime the immune system. This project aims to detail the precise effects that lasers have on eye cells, cell populations and the body as a whole. Laser treatments for sight problems are increasing but the effects of these laser applications on the unique immune systems of the eye and brain are unknown. Previous work of the researchers has shown that a novel nanosecond laser when targeted to the eye can alter cells in the lasered eye and in the unlasered eye and the brain. This kn ....Using lasers to prime the immune system. This project aims to detail the precise effects that lasers have on eye cells, cell populations and the body as a whole. Laser treatments for sight problems are increasing but the effects of these laser applications on the unique immune systems of the eye and brain are unknown. Previous work of the researchers has shown that a novel nanosecond laser when targeted to the eye can alter cells in the lasered eye and in the unlasered eye and the brain. This knowledge may be crucial for enhancing our understanding of the immune privileged state of the eye. In addition, it seeks to guide the development of future low energy lasers as important successful treatments.Read moreRead less
Interaction Of TRP Channels And Inflammatory Mediators: A Critical Role In Visceral Pain
Funder
National Health and Medical Research Council
Funding Amount
$308,747.00
Summary
Transient receptor potential, or TRP channels, are involved in generating many of the sensations we feel, such as touch and pain. The function of these channels can be altered by substances released by the body during inflammation. Some TRP channels have specialized roles in signalling pain from the colon which can be enhanced during colonic inflammation. Understanding how TRP channels and inflammatory mediators function and interact is essential if we are to find treatments for colonic pain.
Deep Learning that Scales. Deep learning has dramatically improved the accuracy of a breathtaking variety of tasks in AI such as image understanding and natural language processing. This project addresses fundamental bottlenecks when attempting to develop deep learning applications at scale. First, this project proposes efficient neural architecture search that is orders of magnitude faster than previously reported, abstracting away the most complex part of deep learning. Second, we will desig ....Deep Learning that Scales. Deep learning has dramatically improved the accuracy of a breathtaking variety of tasks in AI such as image understanding and natural language processing. This project addresses fundamental bottlenecks when attempting to develop deep learning applications at scale. First, this project proposes efficient neural architecture search that is orders of magnitude faster than previously reported, abstracting away the most complex part of deep learning. Second, we will design very efficient binary networks, enabling large-scale deployment of deep learning to mobile devices. Thus this project will overcome two primary limitations of deep learning generally, however, and will greatly increase its already impressive domain of practical application.Read moreRead less
Neourobiology Of Human Epilepsy: Genes, Cellular Mechanisms,network And Whole Brain
Funder
National Health and Medical Research Council
Funding Amount
$17,652,824.00
Summary
The team is comprised of neurologists, molecular geneticists, physiologists and brain imaging specialists and leads the world in the discovery of the genetic causes of epilepsy. They will continue to identify genes underlying epilepsy and study how genetic variations result in development of seizures. Advanced brain imaging will be used to understand the effects of genetic variation on brain structure and function. This study may lead to new diagnostic methods and treatments for epilepsy.
New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project wil ....New Paradigms for Robust Fitting: Kernelisation and Polyhedral Search. Outliers inevitably exist in visual data due to imperfect data acquisition or preprocessing. To enable computer vision applications that can perform reliably, robust fitting algorithms are necessary to counter the biasing influence of outliers. However, current robust algorithms are unsatisfactory: they are unreliable (due to using randomisation) or too computationally costly (due to using exhaustive search). This project will develop new robust algorithms to mitigate these shortcomings. It will do so by investigating two new paradigms of kernelisation and polyhedral search, which offer unprecedented theoretical insights into the problem. The outcomes will contribute towards computer vision applications that are more practical and reliable.Read moreRead less
Continuously learning to see. The ultimate goal of computer vision is to make a machine able to understand the world through analysis of images or videos. The new machine learning techniques developed in this project will enable previously impossible methods of computer vision and help strengthen Australia's competitiveness in this important area.
Understanding and Modelling Insect Motion Vision. The interdisciplinary project proposed will offer a stimulating environment for research/training into computational neuroscience, an attractive area for aspiring scientists. We have already demonstrated the feasibility of transferring physiology into applications, and expect this project to deliver functional motion vision models and devices. Our proposed work will have an impact beyond the advancement of neuro-physiology as knowledge gained is ....Understanding and Modelling Insect Motion Vision. The interdisciplinary project proposed will offer a stimulating environment for research/training into computational neuroscience, an attractive area for aspiring scientists. We have already demonstrated the feasibility of transferring physiology into applications, and expect this project to deliver functional motion vision models and devices. Our proposed work will have an impact beyond the advancement of neuro-physiology as knowledge gained is applicable in a range of areas, with applications in miniature unmanned vehicles and collision avoidance detectors in defence and civilian roles. Our project could also assist in the development of artificial intelligence and as a basis for designing implantable artificial eyes.Read moreRead less
Epilepsy: Molecular Basis And Mechanisms In The Era Of Functional Genomics
Funder
National Health and Medical Research Council
Funding Amount
$12,062,533.00
Summary
The team comprises of neurologists with a special interest in epilepsy (both adult and child) molecular geneticists, physiologists and brain imaging specialists. The team leads the world in the discovery of the genetic causes of epilepsy and epilepsy associated with intellectual disability. The team will continue to identify the genes underlying epilepsy, and study how genetic variations result in the development of seizures and will continue to develop advanced imaging techniques for these stud ....The team comprises of neurologists with a special interest in epilepsy (both adult and child) molecular geneticists, physiologists and brain imaging specialists. The team leads the world in the discovery of the genetic causes of epilepsy and epilepsy associated with intellectual disability. The team will continue to identify the genes underlying epilepsy, and study how genetic variations result in the development of seizures and will continue to develop advanced imaging techniques for these studies. This will include extensive laboratory studies, including the development of mice with the exact mutations that we find in the human condition. Stateof-the-art imaging techniques with magnetic resonance and positron emission tomography are used in human subjects to further understand the effects of the mutations on the structure and function of the brain. This will allow deep understanding of how seizures develop and may lead to new diagnostic methods and treatments. The laboratory and clinical aspects of the research are tightly integrated in this internationally leading collaborative program.Read moreRead less
Dissecting The Pseudoexfoliation Syndrome With Complementary Genetic, Proteomic And Biophysical Strategies
Funder
National Health and Medical Research Council
Funding Amount
$490,352.00
Summary
Pseudoexfoliation syndrome (PEX) is an eye condition in which flaky material deposits in the eye, greatly increasing the risk of cataract and glaucoma which can lead to blindness. PEX is also associated with heart disease, strokes and aneurysms. Cataract surgery in PEX patients has a higher rate of complications. In this project we will determine the nature of PEX material and why it forms. This knowlege will facilitate better diagnosis and treatment of PEX preventing associated blindness.