Generative Visual Pre-training on Unlabelled Big Data. This project aims to develop a generative visual pre-training of large-scale deep neural networks on unlabelled big data. Developing pre-trained visual models that are accurate, robust, and efficient for downstream tasks is a keystone of modern computer vision, but it poses challenges and knowledge gaps to existing unsupervised representation learning. Expected outcomes include new theories and algorithms for unsupervised visual pre-training ....Generative Visual Pre-training on Unlabelled Big Data. This project aims to develop a generative visual pre-training of large-scale deep neural networks on unlabelled big data. Developing pre-trained visual models that are accurate, robust, and efficient for downstream tasks is a keystone of modern computer vision, but it poses challenges and knowledge gaps to existing unsupervised representation learning. Expected outcomes include new theories and algorithms for unsupervised visual pre-training, which are anticipated to deepen our understanding of visual representation and make it easier to build and deploy computer vision applications and services. Examples of benefits include modernising machines in manufacturing and farming with visual intelligence. 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
Advancing future primary teachers' engagement in science inquiry learning. Australia's challenges in regard to scientific literacy and growth of student enrolments in science need to be addressed at multiple levels, starting with the preparation of future primary teachers. Promoting children's early interest in inquiry-based science is essential, yet a challenge for many teachers. This project examines the complex and dynamic interplay of cognitive, metacognitive and emotional processes in futur ....Advancing future primary teachers' engagement in science inquiry learning. Australia's challenges in regard to scientific literacy and growth of student enrolments in science need to be addressed at multiple levels, starting with the preparation of future primary teachers. Promoting children's early interest in inquiry-based science is essential, yet a challenge for many teachers. This project examines the complex and dynamic interplay of cognitive, metacognitive and emotional processes in future primary teachers' engagement in collaborative inquiry-based science activities. A comprehensive intervention based on these insights aims to determine how scaffolding productive engagement can improve the quality of primary teachers' preparation for inquiry-based science.Read moreRead less
International collaboration in teaching and learning of Einsteinian physics. Following a previous project that showed that it is possible and beneficial to teach the modern Einsteinian paradigm of space, time, matter, light and gravity to students as young as 8 years old, this project aims to test and evaluate a seamless progression of learning modern physics through primary and secondary school. It will sequence, integrate and test research-informed teaching and learning materials, and assessme ....International collaboration in teaching and learning of Einsteinian physics. Following a previous project that showed that it is possible and beneficial to teach the modern Einsteinian paradigm of space, time, matter, light and gravity to students as young as 8 years old, this project aims to test and evaluate a seamless progression of learning modern physics through primary and secondary school. It will sequence, integrate and test research-informed teaching and learning materials, and assessment instruments developed through a 7-nation collaboration. Research across 24 schools will be reviewed by a panel drawn from professional organisations and curriculum authorities, and learning resources will be widely disseminated, with view to worldwide introduction of Einsteinian science at school.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE210101881
Funder
Australian Research Council
Funding Amount
$407,390.00
Summary
Building STEM capacity through literacy engagement in spatial reasoning. This project aims to improve boys and girls' spatial reasoning in preschool (when gender differences emerge) by utilizing an activity that both genders equally access: book reading. Spatial reasoning is critical to achievement in science, technology, engineering and mathematics (STEM). This project will address disproportionate outcomes in spatial reasoning and STEM achievement, particularly among females, by identifying ef ....Building STEM capacity through literacy engagement in spatial reasoning. This project aims to improve boys and girls' spatial reasoning in preschool (when gender differences emerge) by utilizing an activity that both genders equally access: book reading. Spatial reasoning is critical to achievement in science, technology, engineering and mathematics (STEM). This project will address disproportionate outcomes in spatial reasoning and STEM achievement, particularly among females, by identifying effective kinds of spatial learning opportunities for the preschool context. Expected outcomes include an innovative approach to improving spatial reasoning through literacy engagement. This provides significant benefits by creating pathways into STEM and informing targeted interventions.Read moreRead less
Individual Differences in Orientations to Risk and Uncertainty. The main goal of this research project is to extend and integrate three individual-differences approaches to predicting and explaining human judgement and decision making (JDM) and risk-taking behaviours (RTB) under uncertainty: Cognitive-capacity, preferences and dispositions, and dual cognitive process approaches. It will achieve this by studying the joint impact of cognitive style, capacities, and RTB/JDM dispositions on performa ....Individual Differences in Orientations to Risk and Uncertainty. The main goal of this research project is to extend and integrate three individual-differences approaches to predicting and explaining human judgement and decision making (JDM) and risk-taking behaviours (RTB) under uncertainty: Cognitive-capacity, preferences and dispositions, and dual cognitive process approaches. It will achieve this by studying the joint impact of cognitive style, capacities, and RTB/JDM dispositions on performance in appropriate JDM tasks. JDM and RTB are at the root of managing uncertainty, human adaptiveness and rationality. This project will also extend our knowledge of gender differences in JDM and RTB, and lay foundations for systematic cross-cultural studies on this topic.Read moreRead less
Equity and spatial reasoning in students’ mathematics development. The project aims to understand the influence of Spatial-Reasoning on school mathematics. Spatial-Reasoning skills are a significant predictor of achievement in mathematics, and will become increasingly necessary in digital and dynamic environments. Opportunities for disadvantaged students to develop such reasoning skills are limited; they are typically not taught in schools. The project investigates the role and nature of Spatial ....Equity and spatial reasoning in students’ mathematics development. The project aims to understand the influence of Spatial-Reasoning on school mathematics. Spatial-Reasoning skills are a significant predictor of achievement in mathematics, and will become increasingly necessary in digital and dynamic environments. Opportunities for disadvantaged students to develop such reasoning skills are limited; they are typically not taught in schools. The project investigates the role and nature of Spatial-Reasoning in students’ mathematics development; and substantiates the long-term effect of a spatial learning programme on educationally disadvantaged students’ mathematics performance and reasoning. This project is expected to improve disadvantaged students’ spatial reasoning and mathematics skills and their life opportunities.Read moreRead less
Face recognition: Properties and origins of whole-face processing. Humans identify other individuals almost entirely by their faces. Correspondingly, research has demonstrated a "special" style of cognitive processing that is unique to faces (at least in ordinary adults). The present project will address two major theoretical issues: (1) the exact nature of the special processing for faces, and (2) the extent to which it is innate, or learned. New progress in understanding these issues will be m ....Face recognition: Properties and origins of whole-face processing. Humans identify other individuals almost entirely by their faces. Correspondingly, research has demonstrated a "special" style of cognitive processing that is unique to faces (at least in ordinary adults). The present project will address two major theoretical issues: (1) the exact nature of the special processing for faces, and (2) the extent to which it is innate, or learned. New progress in understanding these issues will be made using a series of novel experimental techniques. These techniques isolate the specific contribution of the face recognition system, independent of contributions from object recognition, and from early visual processing.Read moreRead less
Special cognitive processing for faces: Expertise effects, and links to neural mechanisms. Humans identify other individuals primarily by their faces. Evidence from cognitive psychology indicates a special 'whole-face' (as opposed to part-based) style of processing for upright faces. This project will provide new insights into two long-standing issues about the origin of special face processing: (1) whether it derives from generic expert recognition processes or has some face-specific innate co ....Special cognitive processing for faces: Expertise effects, and links to neural mechanisms. Humans identify other individuals primarily by their faces. Evidence from cognitive psychology indicates a special 'whole-face' (as opposed to part-based) style of processing for upright faces. This project will provide new insights into two long-standing issues about the origin of special face processing: (1) whether it derives from generic expert recognition processes or has some face-specific innate component; and (2) the extent to which it can be distinguished from part-based processing at the neural level using both functional brain imaging (fMRI) and adaptation to distorted faces.Read moreRead less
Learning Software Security Analysers with Imperfect Data. This project aims to systematically investigate next-generation learning-based software security analysis to detect vulnerabilities in real-world large-scale software. The expected learning-based foundation will support the handling of imperfect data in order to provide a precise, scalable and adaptive security analysis of the critical software components, thus capturing important security vulnerabilities missed by existing approaches. Th ....Learning Software Security Analysers with Imperfect Data. This project aims to systematically investigate next-generation learning-based software security analysis to detect vulnerabilities in real-world large-scale software. The expected learning-based foundation will support the handling of imperfect data in order to provide a precise, scalable and adaptive security analysis of the critical software components, thus capturing important security vulnerabilities missed by existing approaches. The success of this project will further enhance the international competitiveness of Australian research in this important field and will benefit any Australian industry and business where software systems are deeply-rooted, such as transportation, smart homes, medical devices, defence and finance.Read moreRead less