Interacting with visualisations of extremely large graph structures on large displays. The latest technological progressions have delivered very large data sets that can be modelled as graphs or networks. Examples include: social networks, biological data, and software structures. This project will develop techniques to allow users to visualise the graphs in the entirety and directly interact with data.
Immersive analytics: interactive data analysis using surfaces and spaces. This project aims to explore the potential for new immersive display and interaction technologies to greatly enhance the field of visual data analytics. Humans struggle to understand the masses of complex data they now accumulate. Visual data analytics offers a solution. The project expects to provide practical and theoretical frameworks for immersive data analysis and valuable intellectual property on the first practical ....Immersive analytics: interactive data analysis using surfaces and spaces. This project aims to explore the potential for new immersive display and interaction technologies to greatly enhance the field of visual data analytics. Humans struggle to understand the masses of complex data they now accumulate. Visual data analytics offers a solution. The project expects to provide practical and theoretical frameworks for immersive data analysis and valuable intellectual property on the first practical tools for immersive data analytics. This will provide significant benefits, such as allowing those across government and industry to make more informed decisions from data.Read moreRead less
Learning to Reason in Reinforcement Learning. Deep Reinforcement Learning (RL) uses deep neural networks to represent and learn optimal decision-making policies for intelligent agents in complex environments. However, most RL approaches require millions of episodes to converge to good policies, making it difficult for RL to be applied in real-world scenarios taking significant resources. This project aims to equip RL with capabilities such as counterfactual reasoning and outcome anticipation to ....Learning to Reason in Reinforcement Learning. Deep Reinforcement Learning (RL) uses deep neural networks to represent and learn optimal decision-making policies for intelligent agents in complex environments. However, most RL approaches require millions of episodes to converge to good policies, making it difficult for RL to be applied in real-world scenarios taking significant resources. This project aims to equip RL with capabilities such as counterfactual reasoning and outcome anticipation to significantly reduce the number of interactions required, improve generalisation, and provide the agent with the capability to consider the cause-effects. These improvements would narrow the gap between AI and human capabilities and broaden the adoption of RL in real-world applications.Read moreRead less
Remote presence for guidance on physical tasks. This project aims to transform remote collaboration on physical tasks. Current systems for remote collaboration on physical tasks are not as effective as working face-to-face. This could be overcome by sharing non-verbal cues, designing systems to account for cultural issues, and using a new model of communication. This project will develop theories and interaction methods for remote guidance based on natural non-verbal communication cues and cultu ....Remote presence for guidance on physical tasks. This project aims to transform remote collaboration on physical tasks. Current systems for remote collaboration on physical tasks are not as effective as working face-to-face. This could be overcome by sharing non-verbal cues, designing systems to account for cultural issues, and using a new model of communication. This project will develop theories and interaction methods for remote guidance based on natural non-verbal communication cues and cultural issues. This project is expected to benefit industries with widely distributed multi-cultural workforces such as mining, defence and medicine.Read moreRead less
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
A modelling challenge: bridging the gap between molecular and neuronal networks. We will develop innovative frameworks, which unify small-scale molecular activity with electrical signals in branches of brain cells. This research aims to enhance our understanding how molecular scale phenomena influence brain disease, via studying the model dynamics using cutting-edge techniques on a supercomputer. The socio-economic benefits to Australia include: (i) Enhancing Australia's international reputation ....A modelling challenge: bridging the gap between molecular and neuronal networks. We will develop innovative frameworks, which unify small-scale molecular activity with electrical signals in branches of brain cells. This research aims to enhance our understanding how molecular scale phenomena influence brain disease, via studying the model dynamics using cutting-edge techniques on a supercomputer. The socio-economic benefits to Australia include: (i) Enhancing Australia's international reputation for cutting-edge multidisciplinary research; (ii) international collaborations will be strengthened; (iii) outcomes will potentially lead to commercialisation opportunities; (iv) results will ultimately lay the foundations to explore the cellular and molecular origin of brain disorders.Read moreRead less
Pathways to health and wellbeing through housing: a new causal understanding of relationships, processes and interventions. Does housing make Australians healthier or less healthy, how can we target housing assistance so that it improves individual health and wellbeing? This research answers these questions, it develops new methods for understanding the complex causal relationship between housing and health, and evidence of how housing can improve health and wellbeing.
An advanced framework for multi-agent strategic interactions. Communication security protocols and computer algorithms are expressible in terms of strategic interactions between competing agents, which can be analyzed in a game theory setting. This project will exploit the recent advances in extending this game theory framework to multidimensional spaces, thereby strengthening the theoretical foundations. This will provide new insights into the working of algorithms, potentially improving futur ....An advanced framework for multi-agent strategic interactions. Communication security protocols and computer algorithms are expressible in terms of strategic interactions between competing agents, which can be analyzed in a game theory setting. This project will exploit the recent advances in extending this game theory framework to multidimensional spaces, thereby strengthening the theoretical foundations. This will provide new insights into the working of algorithms, potentially improving future secure key distribution. Multi-agent interactions in higher dimensional spaces are considered intractable using traditional matrix methods and this project will build on our exciting new breakthrough showing that such interactions are tractable using geometric multivectors.Read moreRead less
Closing the housing gap: a spotlight on intergenerational inequalities. This project aims to use never-before analysed combinations of datasets and new data on Australian housing conditions to model the consequences of unequal access to housing and housing wealth among Australians, and to evaluate both individual and national benefits of housing interventions across generations. The consequences of unequal access to housing are different for current and future generational cohorts. This project ....Closing the housing gap: a spotlight on intergenerational inequalities. This project aims to use never-before analysed combinations of datasets and new data on Australian housing conditions to model the consequences of unequal access to housing and housing wealth among Australians, and to evaluate both individual and national benefits of housing interventions across generations. The consequences of unequal access to housing are different for current and future generational cohorts. This project expects to reveal the drivers and health consequences of the intergenerational housing gap. Research-based insights on the intergenerational housing crisis will benefit almost all Australians affected by the unprecedented costs of ownership and renting.Read moreRead less
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