Rethinking the Data-driven Discovery of Rare Phenomena. This project will investigate novel technologies for the data-driven discovery of rare phenomena. Scientific disciplines are increasingly able to generate large amounts of data relevant to key discoveries such as novel photovoltaic materials or explanations of brain seizures. However, these discoveries typically correspond to extremely rare phenomena in high dimensional spaces, which current data science methods are unable to detect. The pr ....Rethinking the Data-driven Discovery of Rare Phenomena. This project will investigate novel technologies for the data-driven discovery of rare phenomena. Scientific disciplines are increasingly able to generate large amounts of data relevant to key discoveries such as novel photovoltaic materials or explanations of brain seizures. However, these discoveries typically correspond to extremely rare phenomena in high dimensional spaces, which current data science methods are unable to detect. The project will fill this void and yield novel methods, publications, and open source software for the data-driven discovery or rare phenomena. Thus, it will expand the capabilities of data science, providing better use of the massive data collections accumulating across science, government, and industry.Read moreRead less
Estimating the Topology of Low-Dimensional Data Using Deep Neural Networks. This project will expand on the superhuman visual capabilities of deep neural networks to allow us to analyse the topology of 3- and 4-dimensional manifolds. While these spaces still count as low-dimensional, 4-dimensional manifolds typically are beyond human visual comprehension. The topology of a manifold describes its essential properties such as the number of connected components, holes, tunnels and cavities of vario ....Estimating the Topology of Low-Dimensional Data Using Deep Neural Networks. This project will expand on the superhuman visual capabilities of deep neural networks to allow us to analyse the topology of 3- and 4-dimensional manifolds. While these spaces still count as low-dimensional, 4-dimensional manifolds typically are beyond human visual comprehension. The topology of a manifold describes its essential properties such as the number of connected components, holes, tunnels and cavities of various dimensions. Traditional methods from computational topology fail in large practical applications due to computational restrictions. We propose an approximation that overcomes previous limitations and can open new doors to data analysis in material science, medical imaging, dynamical systems and other applications.
Read moreRead less
Search strategy optimisation by theory, functional analysis and simulation. This project aims to develop a novel computational platform, based on mathematical, statistical and physical theory, as well as advanced simulations, enabling the quantitative prediction of the optimal search strategy to be adopted by populations of agents searching for scarce targets in any given environment. This could lead to significant impacts on breakthrough developments in cancer immunotherapy, search and rescue r ....Search strategy optimisation by theory, functional analysis and simulation. This project aims to develop a novel computational platform, based on mathematical, statistical and physical theory, as well as advanced simulations, enabling the quantitative prediction of the optimal search strategy to be adopted by populations of agents searching for scarce targets in any given environment. This could lead to significant impacts on breakthrough developments in cancer immunotherapy, search and rescue robotics, ecological and environmental management, and developmental biology.Read moreRead less
Hybrid methods with decomposition for large scale optimization. This project aims to develop advanced approaches for solving large scale real-world optimisation problems that are expensive to evaluate, and difficult to formulate, involving thousands of variables and constraints. The project will make novel contributions to improving state-of-the-art large scale optimisation algorithms in terms of scalability, effectiveness, and efficiency for real-world problem solving. The outcomes of this proj ....Hybrid methods with decomposition for large scale optimization. This project aims to develop advanced approaches for solving large scale real-world optimisation problems that are expensive to evaluate, and difficult to formulate, involving thousands of variables and constraints. The project will make novel contributions to improving state-of-the-art large scale optimisation algorithms in terms of scalability, effectiveness, and efficiency for real-world problem solving. The outcomes of this project will bring about greater understanding of real-world large scale optimisation, and deliver practical solutions to these problems.Read moreRead less
Foundations and advanced algorithms for topological image processing. Building on new links between the mathematical discipline of homology and digital images, this project develops a new class of topology-driven image analysis techniques that will improve the accuracy and reliability of predictions made from the powerful new generation of three dimensional microscopes.
Machine learning in adversarial environments. Machine learning underpins the technologies driving the economies of both Silicon Valley and Wall Street, from web search and ad placement, to stock predictions and efforts in fighting cybercrime. This project aims to answer the question: How can machines learn from data when contributors act maliciously for personal gain?
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.
Unifying Foundations for Intelligent Agents. This project aims to drive forward the development of rigorous foundations for intelligent agents. The agent framework, the expected utility principle, sequential decision theory, and the information-theoretic foundations of inductive reasoning and machine learning have already brought significant order into the previously heterogeneous scattered field of artificial intelligence. This project aims to investigate an information-theoretic approach towar ....Unifying Foundations for Intelligent Agents. This project aims to drive forward the development of rigorous foundations for intelligent agents. The agent framework, the expected utility principle, sequential decision theory, and the information-theoretic foundations of inductive reasoning and machine learning have already brought significant order into the previously heterogeneous scattered field of artificial intelligence. This project aims to investigate an information-theoretic approach towards a unifying foundation for intelligent agents, which has recently spawned impressive applications. The theory is expected to provide a gold standard and valuable guidance for researchers working on smart software.Read moreRead less
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