Discovery Early Career Researcher Award - Grant ID: DE230100761
Funder
Australian Research Council
Funding Amount
$430,504.00
Summary
Identifying biases in news using models of narrative framing. This project aims to develop tools to detect biased narratives and one-sided framing in news stories using novel natural language processing methods to understand the text more deeply. Unlike existing methods, which overly rely on surface word co-occurrences patterns, the novel methods will be able to capture narratives in a more holistic and intuitive manner. Expected outcomes include new modeling techniques grounded in theory and a ....Identifying biases in news using models of narrative framing. This project aims to develop tools to detect biased narratives and one-sided framing in news stories using novel natural language processing methods to understand the text more deeply. Unlike existing methods, which overly rely on surface word co-occurrences patterns, the novel methods will be able to capture narratives in a more holistic and intuitive manner. Expected outcomes include new modeling techniques grounded in theory and a tool to highlight biases with recommendations for diverse sets of news articles. By raising awareness to biased news reporting, the project will benefit Australians through more balanced public discourse on global challenges, such as climate change and health pandemics.Read moreRead less
Human models for accelerated robot learning and human-robot interaction. This project aims to develop novel approaches to teach robots to proficiently interact with humans in a safe and low-cost manner. To achieve this aim, this project will develop novel models from which various human behaviours can be generated and used to train human-robot interaction policies in simulation. Expected outcomes of this project include new computational models of human behaviour built using cognitive science th ....Human models for accelerated robot learning and human-robot interaction. This project aims to develop novel approaches to teach robots to proficiently interact with humans in a safe and low-cost manner. To achieve this aim, this project will develop novel models from which various human behaviours can be generated and used to train human-robot interaction policies in simulation. Expected outcomes of this project include new computational models of human behaviour built using cognitive science theories and limited data and new training schemes for robot learning in simulation. By training robots in simulation with accurate human models, this research will enable fast and safe robot training to support the deployment and adoption of robots in human contexts such as healthcare facilities, homes, and workplaces.Read moreRead less
Constraint-based Reasoning for Multi-agent Pathfinding. Automation is a transformative technology for logistics -- using robots to manipulate inventory allows warehouses to be more efficient, and larger-scale, than ever before. But doing this in practice requires efficient, reliable methods for coordinating ever-larger fleets of robots. These problems are extremely difficult, and current approaches either scale poorly or give weak or no guarantees on solution quality. The project will develop t ....Constraint-based Reasoning for Multi-agent Pathfinding. Automation is a transformative technology for logistics -- using robots to manipulate inventory allows warehouses to be more efficient, and larger-scale, than ever before. But doing this in practice requires efficient, reliable methods for coordinating ever-larger fleets of robots. These problems are extremely difficult, and current approaches either scale poorly or give weak or no guarantees on solution quality. The project will develop transformative approaches to multi-agent pathfinding which can handle industrial size problems, and handle all of the complications that arise in practical applications. This will deliver improved cost-effectiveness and productivity to automated warehouse logistics and other agent coordination problems.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE160100568
Funder
Australian Research Council
Funding Amount
$360,000.00
Summary
Towards reliability in combinatorial optimisation. This project intends to develop techniques to ensure that the solutions reported by optimisation tools are correct and verifiable. Combinatorial optimisation problems, where the best solution must be found from a vast set of possibilities, are central to critical sectors of the economy, including shipping, transit, mining and emergency response. Automated tools for these problems can now solve large industrial examples, however, they are incredi ....Towards reliability in combinatorial optimisation. This project intends to develop techniques to ensure that the solutions reported by optimisation tools are correct and verifiable. Combinatorial optimisation problems, where the best solution must be found from a vast set of possibilities, are central to critical sectors of the economy, including shipping, transit, mining and emergency response. Automated tools for these problems can now solve large industrial examples, however, they are incredibly complex artefacts which are prone to error and difficult to test. New methods for ensuring the correctness of automated tools would allow users to trust that the results returned by these tools are correct when making critical decisions.Read moreRead less
Searching for near-exact protein models. This project aims to develop novel and efficient heuristic-based algorithms leading to near accurate protein tertiary structure models. Knowledge about protein structures is fundamental to our understanding of living systems. The progress on experimental determination of these structures has been extremely limited and remains an open challenge in molecular biology. Computational prediction of protein structures from sequences is emerging as a promising ap ....Searching for near-exact protein models. This project aims to develop novel and efficient heuristic-based algorithms leading to near accurate protein tertiary structure models. Knowledge about protein structures is fundamental to our understanding of living systems. The progress on experimental determination of these structures has been extremely limited and remains an open challenge in molecular biology. Computational prediction of protein structures from sequences is emerging as a promising approach, but its accuracy is far from satisfactory. The software systems developed in this project will be used in structural identification of target proteins in drug design. This will make drug design process more efficient, saving time and cost, potentially saving lives.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
Discovery Early Career Researcher Award - Grant ID: DE230100055
Funder
Australian Research Council
Funding Amount
$445,437.00
Summary
Illuminating the dark Universe with explosive astrophysical events. Explosive astrophysical events are critical to understand what the Universe is made of and its physics. This project aims to single out the most exciting exploding stars and extreme events out of the millions detected each night at the world’s largest optical telescope. It will magnify Australian leadership and optimise investment in astronomical facilities by obtaining unique information before these events fade forever. Expect ....Illuminating the dark Universe with explosive astrophysical events. Explosive astrophysical events are critical to understand what the Universe is made of and its physics. This project aims to single out the most exciting exploding stars and extreme events out of the millions detected each night at the world’s largest optical telescope. It will magnify Australian leadership and optimise investment in astronomical facilities by obtaining unique information before these events fade forever. Expected outcomes include improved knowledge on the nature of exploding stars and the discovery of new events and physical processes. It will benefit the Australian community at large by training young Australians in data-intensive technologies required to lead ground-breaking research and advance our innovative economy.Read moreRead less
Efficient and effective methods for classifying massive time series data. This project aims to transform the theory and practice of time series classification. The current state of the art cannot handle the massive numbers of time series that describe many critical problems facing humanity, such as disease transmission and climate change. This project seeks to develop methods that can analyse dynamic processes at global scale, delivering the most accurate classifiers feasible within a given comp ....Efficient and effective methods for classifying massive time series data. This project aims to transform the theory and practice of time series classification. The current state of the art cannot handle the massive numbers of time series that describe many critical problems facing humanity, such as disease transmission and climate change. This project seeks to develop methods that can analyse dynamic processes at global scale, delivering the most accurate classifiers feasible within a given computational budget. Expected outcomes of this project include efficient, effective and broadly applicable time series classification technologies. This should provide significant benefits to myriad sectors, transforming data science for time series problems and supporting innovation in industry, commerce and government.Read moreRead less
Machine learning techniques for fuel loss detection at service stations. This project aims to develop effective techniques to identify the sources of fuel losses, such as leaks and calibration errors in underground storage tanks at service stations. Monitoring fuel losses at service stations is influenced by many external factors which can be difficult to predict. The project expects to use machine learning to develop the techniques and test them with live data at service stations. The expected ....Machine learning techniques for fuel loss detection at service stations. This project aims to develop effective techniques to identify the sources of fuel losses, such as leaks and calibration errors in underground storage tanks at service stations. Monitoring fuel losses at service stations is influenced by many external factors which can be difficult to predict. The project expects to use machine learning to develop the techniques and test them with live data at service stations. The expected outcomes are a set of tailor-made machine learning techniques for effective fuel loss detection and a software suite that can be easily incorporated into the normal operation of service stations. This should reduce the costs to the petroleum industry from wasteful leaks and the environmental damage caused by these leaks. Read moreRead less
Integrated Planning for Uncertainty-Centric Pilot Assistance Systems. This project aims to deliver a novel pilot assistance system to improve the viability, speed and safety of Helicopter Emergency Medical Services (HEMS) and Search and Rescue (SAR) missions. It will advance fundamental algorithms for probabilistic planning in partially observable scenarios to form the core technology of a pilot assistance system that accounts the various types of uncertainty faced by pilots in a typical HEMS/S ....Integrated Planning for Uncertainty-Centric Pilot Assistance Systems. This project aims to deliver a novel pilot assistance system to improve the viability, speed and safety of Helicopter Emergency Medical Services (HEMS) and Search and Rescue (SAR) missions. It will advance fundamental algorithms for probabilistic planning in partially observable scenarios to form the core technology of a pilot assistance system that accounts the various types of uncertainty faced by pilots in a typical HEMS/SAR missions. It will exploit recent advances in Partially Observable Markov Decision Processes (POMDPs) to recommend robust, safe, and pilot-aware mission and manoeuvring strategies to make HEMS/SAR operations safer for helicopter crews, and more effective for those in need of the service.Read moreRead less