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
Quantum Generative Diffusion Models for Molecular Research. This project will devise quantum generative diffusion models to equip classical counterparts with the ability to harness quantum data that naturally arise in molecular research. Theoretical foundations for analysing fast sampling methods with the help of inductive bias regarding the input data and employed circuits will validate efficient quantum generative diffusion models that have training and sampling advantages over classical count ....Quantum Generative Diffusion Models for Molecular Research. This project will devise quantum generative diffusion models to equip classical counterparts with the ability to harness quantum data that naturally arise in molecular research. Theoretical foundations for analysing fast sampling methods with the help of inductive bias regarding the input data and employed circuits will validate efficient quantum generative diffusion models that have training and sampling advantages over classical counterparts. Outcomes include applications in molecular conformation generation, compound screening, and drug design. The innovative research will significantly benefit Australia’s science, industry and health, and will maintain Australia’s global leading role in quantum machine learning and molecular research.Read moreRead less
The amygdala is an area of the brain that is involved in assigning emotional content to sensory information. Disorders of the amygdala lead to a variety of anxiety-related mental disorders such as panic attacks and post-traumatic stress. This grant will study how the NMDA receptor, which plays a central role in memory formation, works in the amygdala. We will determine the functional role of this receptor in the amygdala and how it may be modified by experience.
Optimising students’ academic trajectories: The role of growth (‘personal best’) goals. Too many students fail to reach their academic potential and, as a result, they risk being systematically denied a sense of academic ‘success’ and progress. Through a focus on academic growth (and ‘personal bests’), this research project traverses complex terrain to identify the role of growth goals and growth goal setting in students’ academic trajectories. It also tackles methodological challenges that have ....Optimising students’ academic trajectories: The role of growth (‘personal best’) goals. Too many students fail to reach their academic potential and, as a result, they risk being systematically denied a sense of academic ‘success’ and progress. Through a focus on academic growth (and ‘personal bests’), this research project traverses complex terrain to identify the role of growth goals and growth goal setting in students’ academic trajectories. It also tackles methodological challenges that have impeded research progress in this compelling area. Through strategic international and institutional links, the research program will identify innovative approaches to academic growth and growth goals that will significantly assist pedagogy and psychology aimed at optimising students’ academic potential.Read moreRead less
The Extinction Of Conditioned Fear And Its Implications For Cue Exposure Therapy
Funder
National Health and Medical Research Council
Funding Amount
$322,430.00
Summary
This project studies extinction of Pavlovian conditioned fear reactions in rats. Extinction of these reactions is an animal model for exposure therapy used in the treatment of anxiety disorders in people. In exposure therapy, the patient, aided by the clinician, confronts trauma-related cues in the absence of any overt danger. The intention of this therapy is to reduce the ability of the trauma-related cues to provoke the fear reactions that are undermining the patient's quality of life. In Pavl ....This project studies extinction of Pavlovian conditioned fear reactions in rats. Extinction of these reactions is an animal model for exposure therapy used in the treatment of anxiety disorders in people. In exposure therapy, the patient, aided by the clinician, confronts trauma-related cues in the absence of any overt danger. The intention of this therapy is to reduce the ability of the trauma-related cues to provoke the fear reactions that are undermining the patient's quality of life. In Pavlovian conditioning, subjects (typically rats) are exposed to a signaling relation between an initially neutral stimulus (e.g., a noise) and a feared outcome (e.g., foot shock). When later repeatedly exposed to the initially neutral but now feared stimulus (the noise) in the absence of the feared outcome, the fear reactions it acquired progressively decline until eventually it fails to elicit any such reactions. The fear reactions are said to have been extinguished. There has been significant progress in understanding the psychological processes and neural mechanisms underlying the acquisition of fear reactions, but much less is known about the processes and mechanisms underlying the extinction of these reactions. The project has two general objectives. The first is to determine the conditions of extinction training that promote long-term loss of fear reactions. The second objective is to determine how the brain controls this extinction of learned fear. Achieving these aims will be significant for two reasons. First, it will contribute to understanding the mechanisms by which animals (including people) learn to adjust their behaviour to bring it into line with the current relations that exist between events in the world. Second, it will provide important information about how such adjustment is facilitated or impaired across extinction training and, thereby, contribute towards understanding both the successes and failures of cue exposure therapy for fear-related disorders.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230100495
Funder
Australian Research Council
Funding Amount
$422,154.00
Summary
Structured Federated Learning for Personalised Intelligence on Devices. The project aims to develop a new structured federated machine-learning framework to enhance the customisation of artificial intelligence across mobile and smart devices. It seeks to enable users to receive customised services on their devices without sending their sensitive personal data to a cloud service provider. Anticipated benefits include greater privacy, data security and device performance, as well as better end-use ....Structured Federated Learning for Personalised Intelligence on Devices. The project aims to develop a new structured federated machine-learning framework to enhance the customisation of artificial intelligence across mobile and smart devices. It seeks to enable users to receive customised services on their devices without sending their sensitive personal data to a cloud service provider. Anticipated benefits include greater privacy, data security and device performance, as well as better end-user experience. Expected outcomes of this research include new knowledge, toolkits and algorithms for use in developing machine-learning based secure, efficient and fault-tolerant technologies for software applications, mobile services, cloud computing, autonomous vehicles and advanced manufacturing processes.Read moreRead less
Solving the inert knowledge problem. A central goal of education is for students to transfer what they learn to new contexts or problems. Indeed, expert reasoning is often characterised by seeing the deep structural commonalities across seemingly disparate situations. However, the knowledge students acquire is notoriously inert, tied to the specifics of the learning examples. This project aims to move towards solving 'the inert knowledge problem' by investigating how humans learn concepts define ....Solving the inert knowledge problem. A central goal of education is for students to transfer what they learn to new contexts or problems. Indeed, expert reasoning is often characterised by seeing the deep structural commonalities across seemingly disparate situations. However, the knowledge students acquire is notoriously inert, tied to the specifics of the learning examples. This project aims to move towards solving 'the inert knowledge problem' by investigating how humans learn concepts defined by abstract relational structure, and by designing educational applications that enhance the use of relational learning mechanisms in students with a wide range of cognitive abilities.Read moreRead less
Excellent researchers: Using learner profiles to enhance research learning. Recent evidence concerning metacognitive learning and affect reveals that research degree candidates are a diverse group of learners, and little is known about explaining wasteful attrition, stress and delays in progress. Such a study is essential, especially given the growth in research degrees, new transitional pathways, diversity in candidate backgrounds and chronic high attrition. This longitudinal study applies new ....Excellent researchers: Using learner profiles to enhance research learning. Recent evidence concerning metacognitive learning and affect reveals that research degree candidates are a diverse group of learners, and little is known about explaining wasteful attrition, stress and delays in progress. Such a study is essential, especially given the growth in research degrees, new transitional pathways, diversity in candidate backgrounds and chronic high attrition. This longitudinal study applies new findings about doctoral learning profiles in a direct intervention (DOCLearnPro) that targets individual differences across students in doctoral and master’s degrees to improve learning outcomes significantly and contribute theoretically, methodologically and substantively in order to advance understanding of researcher development.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
Transforming primary teachers' representational practices: effects on students' scientific reasoning and discourse within contemporary sciences. Training teachers to appropriately represent and communicate scientific information is critically important for promoting scientific thinking and learning in students. This research is critical to securing Australia's future interests in developing new and emerging frontier science and technologies through the engagement and retention of students.