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
Data analytics-based tools and methods to enhance self-regulated learning. This project aims to develop student self-regulated learning skills by harnessing the potential of Big Data analytics. The project expects to generate new knowledge at the intersection of learning analytics, educational technology, learning sciences and teaching practice resulting from novel data collection and analysis tools and methods. The outputs are expected to include insights into metacognitive, motivational, and t ....Data analytics-based tools and methods to enhance self-regulated learning. This project aims to develop student self-regulated learning skills by harnessing the potential of Big Data analytics. The project expects to generate new knowledge at the intersection of learning analytics, educational technology, learning sciences and teaching practice resulting from novel data collection and analysis tools and methods. The outputs are expected to include insights into metacognitive, motivational, and technical issues facing analytics-based personalised feedback. The outcomes are intended to offer benefits for developing pedagogical and the design of educational technology. The outcomes can result in improved student learning outcomes in higher education to ensure graduates are prepared for the digital economy.Read moreRead less
Teaching how to learn: promoting self-regulated learning in STEM classes. This project aims to investigate key factors that influence change in teacher practices and student achievement in Science, Technology, Engineering and Mathematics (STEM). It will involve the development and evaluation of interventions designed to help teachers create learning environments that promote student engagement and the development of the cognitive and metacognitive skills needed for success in STEM. The project w ....Teaching how to learn: promoting self-regulated learning in STEM classes. This project aims to investigate key factors that influence change in teacher practices and student achievement in Science, Technology, Engineering and Mathematics (STEM). It will involve the development and evaluation of interventions designed to help teachers create learning environments that promote student engagement and the development of the cognitive and metacognitive skills needed for success in STEM. The project will advance our understanding of how to increase the quality of teaching and learning in STEM subjects. Improving teacher capacity and student performance in STEM is a national priority with significant social and economic benefits to Australia.Read moreRead less
Literacy Instruction for Children with Autism. There is a social and economic imperative to assist all individuals to reach their full potential with regard to literacy skills. The central goal of the proposed research is to develop and evaluate new ways to support comprehensive literacy instruction for children with autism spectrum disorder (ASD). Following our world-first pilot research, we will investigate the efficacy of the ABRACADABRA literacy instruction program delivered in small groups ....Literacy Instruction for Children with Autism. There is a social and economic imperative to assist all individuals to reach their full potential with regard to literacy skills. The central goal of the proposed research is to develop and evaluate new ways to support comprehensive literacy instruction for children with autism spectrum disorder (ASD). Following our world-first pilot research, we will investigate the efficacy of the ABRACADABRA literacy instruction program delivered in small groups of children with ASD supplemented by a novel parent-child shared book reading program. Immediate outcomes extend beyond advances in the science of reading to upskilling parents and professionals who support children with ASD, and provision of tangible life-long benefits for individuals with ASD.Read moreRead less
Learning how people read: Models, brains, big data and maths. Aims: This project aims to understand how people read. We will use novel mathematical methods, experimentation, brain imaging and computational modelling to adjudicate between model predictions.
Significance: This project expects to develop methods to understand and test important aspects of reading.
Expected outcomes: Expected outcomes are the development of novel methods for understanding complex models and the collection of data t ....Learning how people read: Models, brains, big data and maths. Aims: This project aims to understand how people read. We will use novel mathematical methods, experimentation, brain imaging and computational modelling to adjudicate between model predictions.
Significance: This project expects to develop methods to understand and test important aspects of reading.
Expected outcomes: Expected outcomes are the development of novel methods for understanding complex models and the collection of data that can extend and falsify current models of reading.
Benefits: These developments will significantly increase our understanding of how people read and what causes dyslexia. This work will also provide new ways to evaluate complex computational psychological models.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE240100967
Funder
Australian Research Council
Funding Amount
$366,000.00
Summary
Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected o ....Open-world computer vision by detecting and tracking hierarchical objects. This project examines the problem of detecting and tracking objects using computer vision. A fundamental limitation of current algorithms is that they require labelled training data for every object class and therefore cannot be trusted to operate in unconstrained environments. This project aims to address this limitation using novel techniques that incorporate hierarchical relationships between object classes. Expected outcomes include new paradigms for algorithm design and evaluation, and establishing the problem as a focus of international research. The key practical benefit would be to accelerate the wider deployment of visual perception in applications such as autonomous vehicles, interactive robotics, and video analysis.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
Designing Learning Spaces for Diversity, Inclusion and Participation. This project aims to provide evidence-based guidance on how to design and/or modify mainstream schools to make it easier for students with disabilities to participate. It seeks to inform architects, educators, and policy makers about disabled students' spatial requirements and to develop strategies and tools to support the process of co-designing schools with people with lived experience of disability. The outcomes will includ ....Designing Learning Spaces for Diversity, Inclusion and Participation. This project aims to provide evidence-based guidance on how to design and/or modify mainstream schools to make it easier for students with disabilities to participate. It seeks to inform architects, educators, and policy makers about disabled students' spatial requirements and to develop strategies and tools to support the process of co-designing schools with people with lived experience of disability. The outcomes will include an inclusive learning spaces design framework. This is expected to benefit all students' access and meaningful involvement in learning through the development of more inclusive learning spaces. The research is significant because it integrates previously dissociated knowledge from architecture, education and health.Read moreRead less
Reducing self-harm and suicidal behaviours in young people in WA. Aims: reduce self-harm and suicidal behaviours in young people by upskilling teachers and providing resources to respond rapidly to students at risk via an innovative intervention with near real-time measures of changes in vulnerability.
Significance: self-harm and suicidal behaviours are increasing at alarming rates in young people. Schools are ideally placed to respond but many struggle to do so. New regular measures and advance ....Reducing self-harm and suicidal behaviours in young people in WA. Aims: reduce self-harm and suicidal behaviours in young people by upskilling teachers and providing resources to respond rapidly to students at risk via an innovative intervention with near real-time measures of changes in vulnerability.
Significance: self-harm and suicidal behaviours are increasing at alarming rates in young people. Schools are ideally placed to respond but many struggle to do so. New regular measures and advanced machine learning algorithms measuring change in risk in real time will enable schools to respond in a timely and effective manner
and save lives.
Expected outcomes: a new intervention to reduce self-harm and suicidal behaviours in young people that measures fluctuations in risk via a Temporal Vulnerability Index.Read moreRead less
Build competency aware and assuring machine learning systems. Recent development in machine learning (ML) has seen ML models with extremely high prediction accuracy. However, to support human-machine partnership in decision-making in complex environments, beyond accuracy, it is essential for ML systems to be competency aware and reliable, and at the same time be exploratory. This project aims to develop novel techniques to equip a ML system with the ability to identify own competency, to justify ....Build competency aware and assuring machine learning systems. Recent development in machine learning (ML) has seen ML models with extremely high prediction accuracy. However, to support human-machine partnership in decision-making in complex environments, beyond accuracy, it is essential for ML systems to be competency aware and reliable, and at the same time be exploratory. This project aims to develop novel techniques to equip a ML system with the ability to identify own competency, to justify its competency and decisions, to explore unknown situations and fully utilise existing expertise to deal with unknowns. The expected outcomes of the project will enable ML systems to become truely intelligent and reliable machine partners for human decision makers in a wide range of applications.Read moreRead less