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.
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
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
Construction of near optimal oscillatory regimes in singularly perturbed control systems via solutions of Hamilton-Jacobi-Bellman inequalities. Problems of optimal control of systems evolving in multiple time scales arise in a great variety of applications (from diet to environmental modelling). This project addresses the challenge of analytically and numerically constructing rapidly oscillating controls that would 'near optimally coordinate' the slow and fast dynamics.
Walking with dinosaurs in the Kimberley: mapping the Cretaceous landscapes of the Dampier Peninsula. The coastline of the Dampier Peninsula, Western Australia, preserves what is arguably one the largest and most significant stretches of dinosaur track-sites in the world. Despite recent National Heritage listing, the majority of these tracksites are largely undocumented, such that their full scientific significance is poorly understood. The aim of this project is to digitally map the dinosaur tra ....Walking with dinosaurs in the Kimberley: mapping the Cretaceous landscapes of the Dampier Peninsula. The coastline of the Dampier Peninsula, Western Australia, preserves what is arguably one the largest and most significant stretches of dinosaur track-sites in the world. Despite recent National Heritage listing, the majority of these tracksites are largely undocumented, such that their full scientific significance is poorly understood. The aim of this project is to digitally map the dinosaur tracksites of the Dampier Peninsula, utilising high-resolution aerial photography with both manned and unmanned aircraft, airborne and hand-held LiDAR imaging, and digital photogrammetry. The results will allow us to construct high-resolution, three-dimensional digital outcrop models of the tracksites, and bring the 130 million-year-old landscapes back to life.Read moreRead less
Where do inductive biases come from? A Bayesian investigation. This project aims to investigate the origin of our thinking and learning biases using state-of-the-art mathematical models and sophisticated experimental designs. Expected outcomes include bridging the gap between human and machine learning by pairing mathematical modelling with experimental work, forming a necessary step toward the development of machine systems that can reason like people do. This will provide significant benefits ....Where do inductive biases come from? A Bayesian investigation. This project aims to investigate the origin of our thinking and learning biases using state-of-the-art mathematical models and sophisticated experimental designs. Expected outcomes include bridging the gap between human and machine learning by pairing mathematical modelling with experimental work, forming a necessary step toward the development of machine systems that can reason like people do. This will provide significant benefits such as understanding how people operate so effectively in real environments, when even the most powerful computers struggle to handle the complexities of everyday learning problems.Read moreRead less
Decomposition and Duality: New Approaches to Integer and Stochastic Integer Programming. Because of their rich modelling capabilities, integer programs are widely used in industry for decision making and planning. However their solution algorithms do not have the maturity of their cousins in convex optimisation, where the theory of strong duality is ubiquitous. Efficient methods for convex optimisation under uncertainty do not apply to the integer case, which is highly non-convex. Furthermore, i ....Decomposition and Duality: New Approaches to Integer and Stochastic Integer Programming. Because of their rich modelling capabilities, integer programs are widely used in industry for decision making and planning. However their solution algorithms do not have the maturity of their cousins in convex optimisation, where the theory of strong duality is ubiquitous. Efficient methods for convex optimisation under uncertainty do not apply to the integer case, which is highly non-convex. Furthermore, integer models usually assume the data is known with certainty, which is often not the case in the real world. This project will develop new theory and algorithms to enhance the analysis of integer models, including those that incorporating uncertainty, while also enabling the use of parallel computing paradigms. Read moreRead less
Target detection in three-dimensional optic flow. This project aims to understand the behavioural, neural, and computational mechanisms underlying the visualisation of moving targets. Insects have poorer eyesight and smaller brains than humans, but can chase small targets at high speed. This project will use intracellular electrophysiology, information content analysis and model development to decipher the underlying neural tuning mechanisms of hoverflies, which could suggest advanced computatio ....Target detection in three-dimensional optic flow. This project aims to understand the behavioural, neural, and computational mechanisms underlying the visualisation of moving targets. Insects have poorer eyesight and smaller brains than humans, but can chase small targets at high speed. This project will use intracellular electrophysiology, information content analysis and model development to decipher the underlying neural tuning mechanisms of hoverflies, which could suggest advanced computational optimisation and miniaturisation. The project may generate algorithms for rapid and reliable information extraction from large, noisy inputs, useful for developing unmanned vehicles and in Big Data analysis. The results could be useful in developing anti-collision control systems in vehicles using less computational power.Read moreRead less
Automated analysis of multi-modal medical data using deep belief networks. This project will develop an improved breast cancer computer-aided diagnosis (CAD) system that incorporates mammography, ultrasound and magnetic resonance imaging. This system will be based on recently developed deep learning techniques, which have the capacity to process multi-modal data in a unified and optimal manner. The advantage of this technique is that it is able to automatically learn both the relevant features t ....Automated analysis of multi-modal medical data using deep belief networks. This project will develop an improved breast cancer computer-aided diagnosis (CAD) system that incorporates mammography, ultrasound and magnetic resonance imaging. This system will be based on recently developed deep learning techniques, which have the capacity to process multi-modal data in a unified and optimal manner. The advantage of this technique is that it is able to automatically learn both the relevant features to analyse in each modality and the hidden relationships between them. The use of deep belief networks has produced promising results in several fields, such as speech recognition, and so this project believes that our approach has the potential to improve both the sensitivity and specificity of breast cancer detection.Read moreRead less
Occupational measures, perturbations and complex deterministic systems. When tackling complex problems, scientists and engineers seek methods that judiciously exploit stochasticity and perturbations as antidotes to unpredictability of outputs that the latter can induce if they inadvertently influence their models. The project proposes for this study vaccine-like perspective of stochasticity and singular perturbations.