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
Deep Adder Networks on Edge Devices. This project aims to empower edge devices with intelligence by developing advanced deep neural networks that address the conflict between the high resource requirements of deep learning and the generally inadequate performance of the edge. Multiplication has been the dominant type of operation in deep learning, though the addition is known to be much cheaper. This project expects to yield theories and algorithms that allow deep neural networks consisting of n ....Deep Adder Networks on Edge Devices. This project aims to empower edge devices with intelligence by developing advanced deep neural networks that address the conflict between the high resource requirements of deep learning and the generally inadequate performance of the edge. Multiplication has been the dominant type of operation in deep learning, though the addition is known to be much cheaper. This project expects to yield theories and algorithms that allow deep neural networks consisting of nearly pure additions to fulfil the requisites of accuracy, robustness, calibration and generalisation in real-world computer vision tasks. The success of this project will benefit deep learning-based products on smartphones or robots in health and cybersecurity.Read moreRead less
Spatial Cognition—Expressive Representation Formalisms and Effective Reasoning Mechanisms. The project will contribute significantly to the advancement of knowledge in breakthrough science in qualitative spatial reasoning and smart information use in geographic information systems. Expressive spatial languages are important in organising spatial knowledge, defining spatial query languages and guiding spatial data mining. Effective spatial reasoning mechanisms bring theory closer to applications ....Spatial Cognition—Expressive Representation Formalisms and Effective Reasoning Mechanisms. The project will contribute significantly to the advancement of knowledge in breakthrough science in qualitative spatial reasoning and smart information use in geographic information systems. Expressive spatial languages are important in organising spatial knowledge, defining spatial query languages and guiding spatial data mining. Effective spatial reasoning mechanisms bring theory closer to applications including consistency checking and spatial query pre-processing. The project will help in extracting knowledge from massive spatial databases, meeting the growing needs of naive users for spatial information and establishing Australia as a major player in spatial cognition research and in the development of geo-location services.Read moreRead less
Inventiveness and the progress of product innovation. Quantitative models of inventiveness will be used to forecast the potential rate of improvement of a technology and to re-design products to improve more rapidly and steadily. By focusing on innovation in products and technologies in energy conversion, this research can guide development funding for low-carbon energy generation.
How is information organised in the mind? Learning structured mental representations from data. One of the biggest questions in psychology is to understand the principles that the mind uses to organise information. This project is both a search for these underlying psychological laws, and an attempt to develop new statistical technologies and mathematical tools that can be used to organise information in applied settings.
Attention please! Selective attention and human associative learning. Selective attention allows us to pick useful pieces of information out of the mass of stimulation that we're faced with every moment. This project investigates how what we've previously learnt about the significance of events influences whether we'll pick them out as useful in future, and how this might be impaired by old age or mental disorder.
Algorithmic and computational advances in geometric group theory. This project aims to combine new algorithmic ideas, high performance computing and experimental mathematics to answer many outstanding questions in the field of geometric group theory. This project will put Australia at the forefront of new computer-assisted research, and give new insights into complex mathematical problems.
Algorithmics for visual analytics of massive complex networks. The project will provide new scalable algorithms for visual analytics of massive complex networks. These fast algorithms will enable security analysts to detect abnormal behaviours such as money laundering, biologists to understand protein-protein interaction networks, and support software engineers new ways of understanding large software systems.
Next-generation techniques for analysing massive data sets. To process enormous amounts of data, leading computing companies are turning to modern computing frameworks, for which little theory of efficient computational techniques has been developed. This project will resolve key theoretical questions and provide fast techniques for poorly understood pattern recognition and bioinformatics problems.
The role of social-emotional learning in attaining literacy and numeracy. This project aims to characterise variability in developmental pathways to literacy and numeracy, and the factors that contribute to this variation, utilising innovative analytical approaches and population data. This project expects to generate new knowledge regarding the role of school-based social-emotional learning programs in supporting children’s achievement of literacy and numeracy. Expected outcomes of the project ....The role of social-emotional learning in attaining literacy and numeracy. This project aims to characterise variability in developmental pathways to literacy and numeracy, and the factors that contribute to this variation, utilising innovative analytical approaches and population data. This project expects to generate new knowledge regarding the role of school-based social-emotional learning programs in supporting children’s achievement of literacy and numeracy. Expected outcomes of the project include enhanced collaboration with government to deliver policy-relevant information on the most effective targets and timing for delivering social-emotional programs that maximise academic learning. This should assist policy makers to develop better strategies to support every child’s academic achievement.Read moreRead less