A cloud computing environment for managing foreign exchange risk. This project involves using parallel computing and machine learning to improve the real-time handling of a bank's foreign exchange risk. It will lead to improved techniques to manage exchange rate variations, enabling banks to better assess their risk and will ultimately lead to improved services for Australian companies.
Discovery Early Career Researcher Award - Grant ID: DE130101605
Funder
Australian Research Council
Funding Amount
$289,000.00
Summary
Composing machine learning via market mechanisms. This project aims to better understand connections between learning algorithms and markets as aggregators of information and develop new, principled techniques for combining predictions. This will improve our ability to construct systems that make predictions based on multiple, complex and structured sources of data.
Discovery Early Career Researcher Award - Grant ID: DE200101465
Funder
Australian Research Council
Funding Amount
$419,498.00
Summary
Minimising Human Efforts to Fight Fake News and Restore the Public Trust. Our modern society is struggling with an unprecedented amount of online fake news, which is recently driven by misused artificial intelligence (AI) technologies. This project aims to build the first real-time system integrating algorithmic models and human validators to counter such falsehoods, especially those AI-fabricated false stories. This project expects to deliver a series of cost-effective and streaming methods emp ....Minimising Human Efforts to Fight Fake News and Restore the Public Trust. Our modern society is struggling with an unprecedented amount of online fake news, which is recently driven by misused artificial intelligence (AI) technologies. This project aims to build the first real-time system integrating algorithmic models and human validators to counter such falsehoods, especially those AI-fabricated false stories. This project expects to deliver a series of cost-effective and streaming methods empowering a Web-based observatory dashboard of fake news propagation. This achieves significant benefits for media organisations, governments, the public, and academia via timely alerts, data-journalism reports, and novel data visualisations of social media landscape to distinguish between legitimate and deceptive contents.Read moreRead less
Challenging big data for scalable, robust and real-time recommendations. With the advent of big data era, recommender systems are facing unprecedented challenges with respect to the four dimensions of big data: big volume, low veracity, high velocity and high variety. This project aims to develop a new generation of cost-effective techniques for scalable, robust and real-time recommendations utilising big data. This project aims to address these challenges to achieve scalable, robust and real-ti ....Challenging big data for scalable, robust and real-time recommendations. With the advent of big data era, recommender systems are facing unprecedented challenges with respect to the four dimensions of big data: big volume, low veracity, high velocity and high variety. This project aims to develop a new generation of cost-effective techniques for scalable, robust and real-time recommendations utilising big data. This project aims to address these challenges to achieve scalable, robust and real-time recommendations. This project will devise a series of cost-effective machine learning methods and schemes to deliver an end-to-end recommender framework. This project has the potential to significantly reduce the energy consumption of large-scale recommender systems as well as facilitating an increase in the use of recommendation applications for big data.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE210100274
Funder
Australian Research Council
Funding Amount
$415,675.00
Summary
Graph Neural Networks for Efficient Decision-making towards Future Grids. This project aims to develop a breakthrough framework for decision-focused learning by integrating explainable graph neural networks and efficient computational methods. It expects to create new methodologies of graph representation learning for unlocking data insight with spatiotemporal knowledge while to build new accelerated optimisation theories for speeding up decision-focused learning model. The expected outcomes wil ....Graph Neural Networks for Efficient Decision-making towards Future Grids. This project aims to develop a breakthrough framework for decision-focused learning by integrating explainable graph neural networks and efficient computational methods. It expects to create new methodologies of graph representation learning for unlocking data insight with spatiotemporal knowledge while to build new accelerated optimisation theories for speeding up decision-focused learning model. The expected outcomes will advance big spatiotemporal data analytics and nonlinear optimisation theory for solving decision-making tasks towards a future energy system. This should promote the Australian power industry transition to a sustainable future grid based on a digitalisation approach to efficient energy management against climate changes.Read moreRead less
Robust learning of dynamic systems. Robots and other autonomous machines use models of the real world to predict the result of their actions and make decisions, but existing methods used for machine-learning are unreliable in many cases and can be easily fooled. This project aims to make machine-learning of dynamic system models reliable, accurate, and secure. The outcomes of this project will be new models and algorithms that ensure safety and increase accuracy of models learned from data. This ....Robust learning of dynamic systems. Robots and other autonomous machines use models of the real world to predict the result of their actions and make decisions, but existing methods used for machine-learning are unreliable in many cases and can be easily fooled. This project aims to make machine-learning of dynamic system models reliable, accurate, and secure. The outcomes of this project will be new models and algorithms that ensure safety and increase accuracy of models learned from data. This project will benefit robotics, control engineering, infrastructure automation, and other fields that demand the capability to model physical systems from limited data. It will also improve cybersecurity by making learning algorithms resilient to deliberate attacks with false data.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE200101100
Funder
Australian Research Council
Funding Amount
$425,613.00
Summary
Towards Robotic Empathy: A human centred approach to future AI machines. The project aims to equip future robots with empathy by developing computational models which can leverage from verbal and non-verbal cues. With recent advances in artificial intelligence research, robots now have better cognitive and function skills, but they lack socio-emotional skills. Since these robots are expected to provide assistance to humans across different domains including rehabilitation, education and health c ....Towards Robotic Empathy: A human centred approach to future AI machines. The project aims to equip future robots with empathy by developing computational models which can leverage from verbal and non-verbal cues. With recent advances in artificial intelligence research, robots now have better cognitive and function skills, but they lack socio-emotional skills. Since these robots are expected to provide assistance to humans across different domains including rehabilitation, education and health care, empowering them with empathetic abilities is important for their success. The project will advance fundamental research in machine learning, affective computing and artificial intelligence to model human behavior, personality traits and emotions for an empathetic human-robot interaction.Read moreRead less
Improving the specificity of affective computing via multimodal analysis. This project aims to develop multimodal affective sensing techniques that can sense very subtle expressions in human moods and emotions. Much research in affective computing has investigated ways to improve the sensitivity of affect sensing approaches, resulting in more accurate estimates of affective states such as emotions or mood. What remains unsolved so far is the issue of specificity. This project will address this i ....Improving the specificity of affective computing via multimodal analysis. This project aims to develop multimodal affective sensing techniques that can sense very subtle expressions in human moods and emotions. Much research in affective computing has investigated ways to improve the sensitivity of affect sensing approaches, resulting in more accurate estimates of affective states such as emotions or mood. What remains unsolved so far is the issue of specificity. This project will address this issue through novel analyses of very subtle cues in facial and vocal expressions of affect embedded in a multimodal deep learning framework. Current approaches can successfully assist in binary classification tasks. This project will tackle the much more difficult problem of developing advanced affective sensing technology to simultaneously handle homogeneous and heterogeneous affect classes as well as continuous range estimates of affect intensity.Read moreRead less
New Statistical Techniques for Galactic Archaeology. This project aims to develop methods that will enable us to exploit new astronomical data. A revolution is under way in stellar astronomy, with new space satellites and Australian survey instruments about to reveal the composition of millions of stars. These data hold the promise of disentangling the origin of our galaxy through identification of star-forming groups that have long ago dispersed into our galaxy. We can also learn about the nucl ....New Statistical Techniques for Galactic Archaeology. This project aims to develop methods that will enable us to exploit new astronomical data. A revolution is under way in stellar astronomy, with new space satellites and Australian survey instruments about to reveal the composition of millions of stars. These data hold the promise of disentangling the origin of our galaxy through identification of star-forming groups that have long ago dispersed into our galaxy. We can also learn about the nuclear and stellar processes that were active in long-dead stars, and hence explain why the Universe is the way it is. This project aims to extend the powerful Minimum Message Length method, never before used in astronomy, to handle this data. This would put us in a unique position to extract new knowledge from the data that will arrive in the next one to five years.Read moreRead less
Decentralised Collaborative Predictive Analytics on Personal Smart Devices. This project tackles the challenging problem of personalised predictive analytics with resource-constrained personal devices and massive-scale data. The knowledge to be generated concerns privacy, fairness, and resource efficiency in the era of Internet of Things. The expected outcomes include a collaborative learning paradigm for building personalised models on personal smart devices in open and fully decentralised sett ....Decentralised Collaborative Predictive Analytics on Personal Smart Devices. This project tackles the challenging problem of personalised predictive analytics with resource-constrained personal devices and massive-scale data. The knowledge to be generated concerns privacy, fairness, and resource efficiency in the era of Internet of Things. The expected outcomes include a collaborative learning paradigm for building personalised models on personal smart devices in open and fully decentralised settings. Privacy and model fairness are core tenets of the paradigm. Personalised predictive analytics is frontier research that will position Australia at the forefront of AI and give business the tools needed to deploy innovative business systems for market exploitation with a secure, equitable and competitive advantage.Read moreRead less