Discovery Early Career Researcher Award - Grant ID: DE200101253
Funder
Australian Research Council
Funding Amount
$349,586.00
Summary
Making Machine Learning Fair(er). This project aims to develop and implement statistical methods to fight against algorithm bias. In doing so, this project expects to generate new knowledge in the mathematical sciences by employing innovative and interdisciplinary approaches to the development of fairness constraints on machine learning algorithms. Fairness will be seen through the lens of invariance, allowing the developed conceptual framework to find broad applications. Expected outcomes of t ....Making Machine Learning Fair(er). This project aims to develop and implement statistical methods to fight against algorithm bias. In doing so, this project expects to generate new knowledge in the mathematical sciences by employing innovative and interdisciplinary approaches to the development of fairness constraints on machine learning algorithms. Fairness will be seen through the lens of invariance, allowing the developed conceptual framework to find broad applications. Expected outcomes of this project include improved techniques for imposing invariance on deep learning algorithms. This should provide significant benefits to the general public by contributing to the advancement of socially responsible and conscientious machine learning.Read moreRead less
A Generic Framework for Verifying Machine Learning Algorithms. This project aims to discover new ways to verify whether decisions made by Artificial Intelligence and Machine Learning algorithms are as per the specifications set by their designers and/or regulatory bodies. The project also provides new methods to align algorithm decisions when they are found to be non-abiding. The outcomes will include new machine learning theories and frameworks for algorithmic assurance. The significance of the ....A Generic Framework for Verifying Machine Learning Algorithms. This project aims to discover new ways to verify whether decisions made by Artificial Intelligence and Machine Learning algorithms are as per the specifications set by their designers and/or regulatory bodies. The project also provides new methods to align algorithm decisions when they are found to be non-abiding. The outcomes will include new machine learning theories and frameworks for algorithmic assurance. The significance of the project is that it will offer a crucial platform for certifying algorithms and thus benefit society and businesses in deciding the right Artificial Intelligence algorithms. Read moreRead less
Categorisation, communication and the local environment. Languages around the world incorporate different systems of categories, and understanding this variation can contribute to a better understanding of similarities and differences between cultures. This project examines how linguistic variation is shaped in part by variation in the local physical and social environment. The methods include computational analyses of large electronic data sets including dictionaries and linguistic corpora tha ....Categorisation, communication and the local environment. Languages around the world incorporate different systems of categories, and understanding this variation can contribute to a better understanding of similarities and differences between cultures. This project examines how linguistic variation is shaped in part by variation in the local physical and social environment. The methods include computational analyses of large electronic data sets including dictionaries and linguistic corpora that have become available only recently, and psychological experiments that probe the causal mechanisms that lead to variation across languages. The outcomes include computational tools that pick out key differences between languages and therefore support cross-cultural communication.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE190100656
Funder
Australian Research Council
Funding Amount
$364,259.00
Summary
The stars that should not exist. This project aims to explain the origin of stars with a chemical composition that is so peculiar that they cannot be explained by any theory of how stars evolve or how elements are created. Their very existence represents fundamental problems in astrophysics. This project proposes a novel method to distinguish peculiarity of up to 20 million stars, mostly observed from Australia. Expected outcomes include new theories to explain two of the most puzzling kinds of ....The stars that should not exist. This project aims to explain the origin of stars with a chemical composition that is so peculiar that they cannot be explained by any theory of how stars evolve or how elements are created. Their very existence represents fundamental problems in astrophysics. This project proposes a novel method to distinguish peculiarity of up to 20 million stars, mostly observed from Australia. Expected outcomes include new theories to explain two of the most puzzling kinds of peculiar stars, discoveries of new kinds of anomalous stars, and discoveries of ancient or metal-free stars that should not exist. The project is expected to generate social benefit, as well as long-term economic benefits by inspiring and training the next generation of data analysts, programmers, engineers, teachers, and scientists. It may also generate economic benefits from a generalised method for outlier detection in high-dimensional datasets.Read moreRead less
Industrial Transformation Training Centres - Grant ID: IC190100031
Funder
Australian Research Council
Funding Amount
$3,973,202.00
Summary
ARC Training Centre in Data Analytics for Resources and Environments (DARE). Understanding the cumulative impact of actions regarding the use of our resources has important long-term consequences for Australia’s economic, societal and environmental health. Yet despite the importance of these cumulative impacts, and the availability of data, many decisions and policies are based on limited amounts of data and rudimentary data analysis, with little appreciation of the critical role that understand ....ARC Training Centre in Data Analytics for Resources and Environments (DARE). Understanding the cumulative impact of actions regarding the use of our resources has important long-term consequences for Australia’s economic, societal and environmental health. Yet despite the importance of these cumulative impacts, and the availability of data, many decisions and policies are based on limited amounts of data and rudimentary data analysis, with little appreciation of the critical role that understanding and quantifying uncertainty plays in the process. The aim of Data Analytics in Resources and Environment (DARE) is to develop and deliver the data science skills and tools for Australia’s resource industries to make the best possible evidence-based decisions in exploiting and stewarding the nation’s natural resources.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE240101089
Funder
Australian Research Council
Funding Amount
$436,847.00
Summary
Trustworthy Hypothesis Transfer Learning. It is urgent to develop a new hypothesis transfer learning scheme that can overcome potential risks when finetuning unreliable large-scale pre-trained models. This project aims to develop an advanced and reliable scheme of hypothesis transfer learning, called Trustworthy Hypothesis Transfer Learning (TrustHTL). A new theoretically guaranteed heterogeneous hypothesis transfer learning framework will be developed to handle heterogeneous situations; a metho ....Trustworthy Hypothesis Transfer Learning. It is urgent to develop a new hypothesis transfer learning scheme that can overcome potential risks when finetuning unreliable large-scale pre-trained models. This project aims to develop an advanced and reliable scheme of hypothesis transfer learning, called Trustworthy Hypothesis Transfer Learning (TrustHTL). A new theoretically guaranteed heterogeneous hypothesis transfer learning framework will be developed to handle heterogeneous situations; a methodology to disinherit risks of pre-trained models and a new fuzzy relation based distributional discrepancy in heterogeneous transfer learning scenarios. The outcomes should significantly improve the reliability of machine learning with benefits for safety learning in data analytics.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
Exploiting Geometries of Learning for Fast, Adaptive and Robust AI. This project aims to uniquely exploit geometric manifolds in deep learning to advance the frontier of Artificial Intelligence (AI) research and applications in cybersecurity and general cognitive tasks. It expects to develop new theories, algorithms, tools, and technologies for machine learning systems that are fast, adaptive, lifelong and robust, even with limited supervision. Expected outcomes will enhance Australia's capabili ....Exploiting Geometries of Learning for Fast, Adaptive and Robust AI. This project aims to uniquely exploit geometric manifolds in deep learning to advance the frontier of Artificial Intelligence (AI) research and applications in cybersecurity and general cognitive tasks. It expects to develop new theories, algorithms, tools, and technologies for machine learning systems that are fast, adaptive, lifelong and robust, even with limited supervision. Expected outcomes will enhance Australia's capability and competitiveness in AI, and deliver robust and trustworthy learning technology. The project should provide significant benefits not only in advancing scientific and translational knowledge but also in accelerating AI innovations, safeguarding cyberspace, and reducing the burden on defence expenses in Australia.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE240100144
Funder
Australian Research Council
Funding Amount
$444,447.00
Summary
Universal Model Selection Criteria for Scientific Machine Learning. This project aims to develop provably reliable universal model selection criteria to facilitate trustworthy scientific machine learning. Combining stochastic methods with an innovative geometric approach to basic statistical principles, this project expects to characterise, combine, and refine the most successful heuristics for designing and training huge models, such as deep neural networks, into a cohesive theoretical framewor ....Universal Model Selection Criteria for Scientific Machine Learning. This project aims to develop provably reliable universal model selection criteria to facilitate trustworthy scientific machine learning. Combining stochastic methods with an innovative geometric approach to basic statistical principles, this project expects to characterise, combine, and refine the most successful heuristics for designing and training huge models, such as deep neural networks, into a cohesive theoretical framework. The expected outcomes include a general toolkit for assisting neural network design at the forefront of scientific applications. This should significantly improve the quality of scientific predictions by facilitating confident adoption of deep learning methods into the pantheon of trustworthy modeling techniques. Read moreRead less
Causal Knowledge-Empowered Adaptive Federated Learning. Federated learning tools are a promising framework for collaborative machine learning (ML) that also maintain data privacy; however, their ability to model heterogeneous data remains a key challenge. This project aims to develop a new learning scheme for coordinated training of ML models that successfully bridges variable data distributions. The framework proposed will be the first globally that can use causal knowledge to 1) handle data he ....Causal Knowledge-Empowered Adaptive Federated Learning. Federated learning tools are a promising framework for collaborative machine learning (ML) that also maintain data privacy; however, their ability to model heterogeneous data remains a key challenge. This project aims to develop a new learning scheme for coordinated training of ML models that successfully bridges variable data distributions. The framework proposed will be the first globally that can use causal knowledge to 1) handle data heterogeneity across devices and 2) address the real-world challenges when only a subset of devices have labelled data. Expected outcomes and benefits include the theoretical underpinnings and algorithms of causality-based collaborative training of ML models while better preserving the users’ data privacy.Read moreRead less