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
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
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
3D Vision Geometric Optimisation in Deep Learning. This project aims to develop a methodology for integrating the algorithms of 3D Vision Geometry and Optimization into the framework of Machine Learning and demonstrate the wide applicability of the new methods on a variety of challenging fundamental problems in Computer Vision. These include 3D geometric scene understanding, and estimation and prediction of human 2D/3D pose and activity. Applications of this technology are to be found in Intell ....3D Vision Geometric Optimisation in Deep Learning. This project aims to develop a methodology for integrating the algorithms of 3D Vision Geometry and Optimization into the framework of Machine Learning and demonstrate the wide applicability of the new methods on a variety of challenging fundamental problems in Computer Vision. These include 3D geometric scene understanding, and estimation and prediction of human 2D/3D pose and activity. Applications of this technology are to be found in Intelligent Transportation, Environment Monitoring, and Augmented Reality, applicable in smart-city planning and medical applications such as computer-enhanced surgery. The goal is to build Australia's competitive advantage in the forefront of ICT research and technology innovation.Read moreRead less
Tracking the Flow of Perceptual Information Through Decision Networks. The choices we make define our lives. Despite exciting progress in neuroscience, we still don’t know how the inner workings of the brain give rise to simple decisions. This project brings together experts from diverse domains of computational neuroscience to investigate how our brains turn perceptual information into action. Together, we will develop new methods to track information flow through the brain during the decision ....Tracking the Flow of Perceptual Information Through Decision Networks. The choices we make define our lives. Despite exciting progress in neuroscience, we still don’t know how the inner workings of the brain give rise to simple decisions. This project brings together experts from diverse domains of computational neuroscience to investigate how our brains turn perceptual information into action. Together, we will develop new methods to track information flow through the brain during the decision making process. By doing so, we will develop a world-leading model of how the brain makes decisions, and also provide the broader scientific community with a set of exciting new tools for studying information processing in the brain.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE210100749
Funder
Australian Research Council
Funding Amount
$434,030.00
Summary
Machine learning of subgrid ocean physics for global ocean models. Climate projections require simulations with ocean-climate models for hundreds of years. Computational resources limit the resolution of our models for such long runs, meaning that some key physical processes remain unresolved and must be parameterised. This project uses machine learning to find new parameterisations for unresolved ocean processes. These new parameterisations will be implemented into computationally cheaper coars ....Machine learning of subgrid ocean physics for global ocean models. Climate projections require simulations with ocean-climate models for hundreds of years. Computational resources limit the resolution of our models for such long runs, meaning that some key physical processes remain unresolved and must be parameterised. This project uses machine learning to find new parameterisations for unresolved ocean processes. These new parameterisations will be implemented into computationally cheaper coarse-resolution ocean models, thereby enhancing these models' representation of the ocean circulation. This project expects to reveal the dynamics of unresolved processes, to improve the accuracy of climate projections and to provide a proof-of-concept for how machine learning can be used in ocean and climate science.Read moreRead less
Making Meta-learning Generalised . This project aims to develop novel machine learning techniques, termed generalised meta-learning, to make machines better utilise past experience to solve new tasks with few data. It expects to reduce the undesirable dependence of current machine learning on labelled data and significantly expand its application scope. Expected outcomes of the project consist of new theoretical results on meta-learning and a set of innovative algorithms that can support the bui ....Making Meta-learning Generalised . This project aims to develop novel machine learning techniques, termed generalised meta-learning, to make machines better utilise past experience to solve new tasks with few data. It expects to reduce the undesirable dependence of current machine learning on labelled data and significantly expand its application scope. Expected outcomes of the project consist of new theoretical results on meta-learning and a set of innovative algorithms that can support the building of next generation of computer vision systems to work in open and dynamic environments. This should be able to produce solid benefits to the science, society, and economy of Australian via the application of these advanced intelligent systems.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
Modelling Adversarial Noise for Trustworthy Data Analytics. Adversarial robustness is a core property of trustworthy machine learning. This project aims to equip machines with the ability to model adversarial noise for defending adversarial attacks. The project expects to produce the next great step for artificial intelligence – the potential to robustly explore and exploit deceptive data. Expected outcomes of this project include theoretical foundations for modelling adversarial noise and the n ....Modelling Adversarial Noise for Trustworthy Data Analytics. Adversarial robustness is a core property of trustworthy machine learning. This project aims to equip machines with the ability to model adversarial noise for defending adversarial attacks. The project expects to produce the next great step for artificial intelligence – the potential to robustly explore and exploit deceptive data. Expected outcomes of this project include theoretical foundations for modelling adversarial noise and the next generation of intelligent systems to accommodate data in a noisy and hostile environment. This should benefit science, society, and the economy nationally and internationally through the applications to trustworthily analyse their corresponding complex data. Read moreRead less
Making sense of ambiguity: brain system interactions and visual uncertainty. This project aims to identify and characterise the interactions between brain regions underlying a fundamental process in visual perception: interpreting sensory input that is unclear or ambiguous. It will use two complementary neuroimaging techniques and cutting-edge analysis methods. The intended outcomes include new insights into a fundamental but poorly characterised aspect of brain function: how brain regions inter ....Making sense of ambiguity: brain system interactions and visual uncertainty. This project aims to identify and characterise the interactions between brain regions underlying a fundamental process in visual perception: interpreting sensory input that is unclear or ambiguous. It will use two complementary neuroimaging techniques and cutting-edge analysis methods. The intended outcomes include new insights into a fundamental but poorly characterised aspect of brain function: how brain regions interact, and advanced analysis methods with wide application. Expected benefits include important advances in knowledge that lay foundations for future study of neural disorders, international collaboration, and new methods placing Australia at the forefront of the international effort to understand the human brain. Read moreRead less