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
Discovering Patterns using Near Unsupervised Leaning to Support the Quick Detection of New Animal Disease Outbreaks Caused by Viruses. Without the capability to identify and study the vast majority of extant viruses using traditional laboratory techniques, emerging threats to Australian livestock health cannot be efficiently diagnosed or treated. New approaches based on high-throughput sequencing have recently been developed to study such viruses, but making sense of the sequence data is still a ....Discovering Patterns using Near Unsupervised Leaning to Support the Quick Detection of New Animal Disease Outbreaks Caused by Viruses. Without the capability to identify and study the vast majority of extant viruses using traditional laboratory techniques, emerging threats to Australian livestock health cannot be efficiently diagnosed or treated. New approaches based on high-throughput sequencing have recently been developed to study such viruses, but making sense of the sequence data is still a complex problem. Together with the project's Partner Organisations, including YourGene Biosciences Australia and the CSIRO Australian Animal Health Laboratory, this project aims to develop new computational methods to broaden the scope of detection and analysis of unknown viruses, enhancing the capability for research into the causative viral agents of animal diseases.Read moreRead less
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
Adaptive modelling of human responses in complex interaction. This project aims to combine strengths of human cognition and evolutionary computing to efficiently solve problems which neither can do alone. The project will develop techniques combining advanced non-intrusive sensor measures of behaviour and emotional reaction in interaction tasks to enable high level computer support for human goal seeking, in complex data and design environments. This project will allow non-expert users to use to ....Adaptive modelling of human responses in complex interaction. This project aims to combine strengths of human cognition and evolutionary computing to efficiently solve problems which neither can do alone. The project will develop techniques combining advanced non-intrusive sensor measures of behaviour and emotional reaction in interaction tasks to enable high level computer support for human goal seeking, in complex data and design environments. This project will allow non-expert users to use tools normally requiring extensive training in settings where the user can 'see' when they get something they like but do not know how to instruct a computer system to show or do it. Applications of the project will include visualisation for bespoke manufacturing or for high dimensional data, generating abstract art, or improving teleconferencing systems.Read moreRead less
Hybridisation leading to lost sex: genomic and experimental insights. The project intends to apply advanced genomics to two classic Australian systems and quantitative genetics to one to address long-standing questions about why asexual reproduction is rare. It aims to test for rapid changes in genomes accompanying hybrid-origins of asexuals and whether this new diversity enables their ongoing evolution. The significance is that support for this hypothesis would challenge current theory for why ....Hybridisation leading to lost sex: genomic and experimental insights. The project intends to apply advanced genomics to two classic Australian systems and quantitative genetics to one to address long-standing questions about why asexual reproduction is rare. It aims to test for rapid changes in genomes accompanying hybrid-origins of asexuals and whether this new diversity enables their ongoing evolution. The significance is that support for this hypothesis would challenge current theory for why sex is so common. The expected outcome is to understand how variation is generated in natural populations with different ways of reproducing. Benefits would include significant contributions to global science, evolutionary training and potential applications in using hybridisation to manage threatened species or pests.Read moreRead less
Conservation genomics of a critically endangered insect. This project aims to develop tools genotyping large animal genomes, focusing on the case of the Lord Howe Island stick insect, once thought to be extinct and now critically endangered. This project expects to generate molecular tools to monitor the genetic health the insect which has a large, complex and poorly understood genome. Expected outcomes include the development of a preservation and reintroduction strategy for the insect. This pr ....Conservation genomics of a critically endangered insect. This project aims to develop tools genotyping large animal genomes, focusing on the case of the Lord Howe Island stick insect, once thought to be extinct and now critically endangered. This project expects to generate molecular tools to monitor the genetic health the insect which has a large, complex and poorly understood genome. Expected outcomes include the development of a preservation and reintroduction strategy for the insect. This project will benefit ongoing conservation efforts, and is timely given the ongoing eradication of rats from Lord Howe Island where this species once lived. Read moreRead less
Understanding climate and harvest induced changes in fish life histories. This project aims to quantify the cumulative impacts of harvest and climate change across marine fishes and ecosystems. The project expects to generate new knowledge in this area by coupling the rich biological information archived in fish ear bones, with targeted multi-generation experiments and predictive modelling. Expected outcomes include fundamental insights into how human-induced environmental change affects fish gr ....Understanding climate and harvest induced changes in fish life histories. This project aims to quantify the cumulative impacts of harvest and climate change across marine fishes and ecosystems. The project expects to generate new knowledge in this area by coupling the rich biological information archived in fish ear bones, with targeted multi-generation experiments and predictive modelling. Expected outcomes include fundamental insights into how human-induced environmental change affects fish growth and maturation, and a subsequent critical evaluation of the sensitivity of fisheries models to trends in these life-history traits. This should provide significant benefits to fisheries and ecosystem management, ensuring they remain productive and resilient in a time of rapid environmental change.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE140101481
Funder
Australian Research Council
Funding Amount
$390,000.00
Summary
Integrating ecology and evolution: how does sexual selection affect population fitness and extinction? Improving our understanding of population fitness could produce important new advances in evolutionary and conservation biology. Sexual selection has been proposed to both help and harm population fitness, but unfortunately these opposing effects have been studied in isolation. This project will develop new theory to resolve confusion over the definition of population fitness and its relationsh ....Integrating ecology and evolution: how does sexual selection affect population fitness and extinction? Improving our understanding of population fitness could produce important new advances in evolutionary and conservation biology. Sexual selection has been proposed to both help and harm population fitness, but unfortunately these opposing effects have been studied in isolation. This project will develop new theory to resolve confusion over the definition of population fitness and its relationship with sexual selection. It also proposes ambitious experimental evolution and quantitative genetic studies that will empirically measure the net effect of sexual selection on population fitness and extinction. This project aims to catalyse a change in the study of population fitness and address a conspicuous gap in contemporary evolutionary biology.Read moreRead less
Mathematics and computing for integrated stockyard-centric management of mining supply chains. Blended mineral products, such as coal and iron ore, make a strong contribution to Australia's economy. Blending occurs in stockpiles, so to realise product value, stockyard and supply chain operational plans must align with blend targets. This project will provide new mathematical and computational planning tools to maximise this value.
Evolution in tooth and claw: exploring the relationship between the radiation of marsupial herbivores and late Cenozoic climate change. Establishing how animals responded to past environmental changes is essential for understanding the ecology of modern species and managing them in light of contemporary climatic trends. By applying several novel analytical methods this project will unravel the links between the radiation of Australian marsupials and key stages in climatic evolution.