Evaluating recurrence as a measure of change in interpersonal dynamics. This project aims to develop an automated conversation analysis system to quantify how communication changes over extended periods of time. It is innovative in proposing to extend the theory and methods of recurrence analysis (a dynamical systems technique) to interacting modalities combining text, audio and video, and to longitudinal analyses. The project is significant in being the first to aim to measure communication dyn ....Evaluating recurrence as a measure of change in interpersonal dynamics. This project aims to develop an automated conversation analysis system to quantify how communication changes over extended periods of time. It is innovative in proposing to extend the theory and methods of recurrence analysis (a dynamical systems technique) to interacting modalities combining text, audio and video, and to longitudinal analyses. The project is significant in being the first to aim to measure communication dynamics over time in the fields of education, health, public discourse and science. It is expected to result in new theories and methods for recurrence analysis validated using real-world data; and to enable new technologies for evaluating professional communication training and communication changes resulting from education or disease progression.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE200101610
Funder
Australian Research Council
Funding Amount
$403,398.00
Summary
Towards Explainable Multi-source Multivariate Time-series Analysis. The aim of this project is to build deep learning models with transparent reasoning behind the results that can be easily interpreted by humans. The research rests on translating pertinent knowledge from multiple sources of complex data containing event sequences into graph form and embedding those knowledge graphs into a sophisticated deep learning model. Such an accomplishment represents the next great advance in machine intel ....Towards Explainable Multi-source Multivariate Time-series Analysis. The aim of this project is to build deep learning models with transparent reasoning behind the results that can be easily interpreted by humans. The research rests on translating pertinent knowledge from multiple sources of complex data containing event sequences into graph form and embedding those knowledge graphs into a sophisticated deep learning model. Such an accomplishment represents the next great advance in machine intelligence and will lay the theoretical foundations for building intelligent analysis tools that truly work in tandem with people. The potential benefits to science, society, and the Australian economy, particularly in finance, sensor technologies, and emergency health services would be appreciable.Read moreRead less
Unlocking Mass Mobile Video Analytics with Advanced Neural Memory Networks. This project will develop neural memory architectures and dense spatial-temporal bundle adjustment to predict movement, behaviour, and perform multi-sensor fusion across large asynchronous video feeds. This capability will allow us to better interrogate and analyse mass video information recorded from the vast number of smartphones, action cameras, and surveillance cameras which exist at public events of interest. Outcom ....Unlocking Mass Mobile Video Analytics with Advanced Neural Memory Networks. This project will develop neural memory architectures and dense spatial-temporal bundle adjustment to predict movement, behaviour, and perform multi-sensor fusion across large asynchronous video feeds. This capability will allow us to better interrogate and analyse mass video information recorded from the vast number of smartphones, action cameras, and surveillance cameras which exist at public events of interest. Outcomes include the ability to ingest multiple video feeds into a dense and dynamic 3D reconstruction for knowledge representation and discovery, and analysis of events and behaviour through new spatio-temporal analytic approaches. This will offer significant benefits for video forensic analysis, policing, and emergency response.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE200101840
Funder
Australian Research Council
Funding Amount
$426,696.00
Summary
Fantastic companions of giant planets and where to find them. The gas giants in the Solar System are hypothesized to have played important roles in the formation and habitability of the Earth. This project aims to put the Solar System in a broader context of the exoplanet demography. The expected outcomes of this project include: (1) a uniform sample of small planets discovered with the public Transiting Exoplanet Survey Satellite data; (2) detection of additional gas giants and in-depth charact ....Fantastic companions of giant planets and where to find them. The gas giants in the Solar System are hypothesized to have played important roles in the formation and habitability of the Earth. This project aims to put the Solar System in a broader context of the exoplanet demography. The expected outcomes of this project include: (1) a uniform sample of small planets discovered with the public Transiting Exoplanet Survey Satellite data; (2) detection of additional gas giants and in-depth characterisation of the best planetary systems; (3) occurrence rate of planetary systems cohosting both gas giant and small planets. This study will provide significant benefits for theoretically understanding the uniqueness of the Solar System, as well as the formation and evolution of planetary systems in general.Read moreRead less
The role of relational information in the guidance of visual attention. The project aims to develop a new theory of attention that describes more accurately which items in the visual field can pop out and grab attention. The potential practical gains of the project are high, as it can lead to significant advancements in robotic vision, transport safety, and provide insights into clinical disorders such as ADHD.
Quantum-Inspired Machine Learning. This project aims to develop new machine learning techniques based around the close correspondence between
neural networks used in deep learning, and tensor networks used in quantum physics. Tensor networks are a form of information compression that is useful in machine learning to construct a compact representation of a large data set in a way that is more amenable to understanding the internal structure than a deep neural network. Expected outcomes of this pr ....Quantum-Inspired Machine Learning. This project aims to develop new machine learning techniques based around the close correspondence between
neural networks used in deep learning, and tensor networks used in quantum physics. Tensor networks are a form of information compression that is useful in machine learning to construct a compact representation of a large data set in a way that is more amenable to understanding the internal structure than a deep neural network. Expected outcomes of this project include more resilient algorithms for machine learning, and new ways to represent quantum states that will impact fundamental physics. The resulting benefits include enhanced capacity for cross-discipline collaboration, and improved methods for future industrial applications.
Read moreRead less
Advancing the visualisation and quantification of nephrons with MRI. . This project aims to characterise key components of nephrons, the glomeruli and tubules, using magnetic resonance imaging without contrast agents, in combination with Deep Learning and super-resolution techniques. Nephrons, the basic functional unit of the kidney, are critical to the maintenance of the body’s homeostasis. Their number and architecture are critical determinants of kidney function. The expected outcomes are inn ....Advancing the visualisation and quantification of nephrons with MRI. . This project aims to characterise key components of nephrons, the glomeruli and tubules, using magnetic resonance imaging without contrast agents, in combination with Deep Learning and super-resolution techniques. Nephrons, the basic functional unit of the kidney, are critical to the maintenance of the body’s homeostasis. Their number and architecture are critical determinants of kidney function. The expected outcomes are innovative semi-automated nephron visualisation and quantitation tools that enable efficient renal phenotyping. Techniques tailored to widely accessible preclinical research scanners are expected to accelerate research into genetic and environmental factors affecting kidney microstructure in embryonic and post-natal life.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE180100923
Funder
Australian Research Council
Funding Amount
$348,575.00
Summary
Efficient second-order optimisation algorithms for learning from big data. This project aims to apply a diverse range of scientific computing techniques to design and implement new, second-order methods that can surpass first-order alternatives in the next generation of optimisation methods for large-scale machine learning (ML). Scalable optimisation methods are now an integral part ML in the presence of “big data”. While the development of efficient first-order methods has grown in the ML comm ....Efficient second-order optimisation algorithms for learning from big data. This project aims to apply a diverse range of scientific computing techniques to design and implement new, second-order methods that can surpass first-order alternatives in the next generation of optimisation methods for large-scale machine learning (ML). Scalable optimisation methods are now an integral part ML in the presence of “big data”. While the development of efficient first-order methods has grown in the ML community, second-order alternatives have largely been ignored. The project expects to facilitate the development of more effective ML algorithms for extraction of knowledge from large data sets.Read moreRead less
RNA structure prediction by deep learning and evolution-derived restraints. This project addresses the long-standing structure-folding problem of Ribonucleic acids (RNA) whose solution is essential for elucidating the roles of noncoding RNAs in living organisms. The proposed approach will detect hidden homologous sequences and enhance evolutionary covariation signals by developing new algorithms for search and smarter neural networks for deep learning. The project expects to generate new tools ....RNA structure prediction by deep learning and evolution-derived restraints. This project addresses the long-standing structure-folding problem of Ribonucleic acids (RNA) whose solution is essential for elucidating the roles of noncoding RNAs in living organisms. The proposed approach will detect hidden homologous sequences and enhance evolutionary covariation signals by developing new algorithms for search and smarter neural networks for deep learning. The project expects to generate new tools for structure-based probing of RNA evolutional and functional mechanisms. The outcomes should provide significant benefits by high-accuracy computational modelling of RNA structures that are difficult and costly to solve by current structural biology techniques but important for enabling biotech and clinical applications.Read moreRead less
Protein structure prediction by deep long-range learning. This project aims to address the challenging problem of protein structure prediction by developing deep long-range learning methods. The project expects to advance protein structure prediction by capturing the long-range interactions through whole sequence learning, rather than short window-based learning. Expected outcomes include next-generation machine-learning techniques for predicting one, two and three-dimensional protein structures ....Protein structure prediction by deep long-range learning. This project aims to address the challenging problem of protein structure prediction by developing deep long-range learning methods. The project expects to advance protein structure prediction by capturing the long-range interactions through whole sequence learning, rather than short window-based learning. Expected outcomes include next-generation machine-learning techniques for predicting one, two and three-dimensional protein structures from their sequences. The expected outcomes should provide significant benefits by computationally determining protein structures beyond homologous sequences, and enabling structure-based drug discovery to disease-causing protein targets previously inaccessible to biotech and pharmaceutical companies.Read moreRead less