Using cognitive models to understand memorability of real world images. This proposal aims to understand and make predictions about which real world images -- specifically living things, objects, and human faces -- that people will remember remember via an integration of cognitive models of memory and machine learning techniques. Computer vision models and similarity scaling techniques will be used to produce psychological representations of the images. These representations will then be integra ....Using cognitive models to understand memorability of real world images. This proposal aims to understand and make predictions about which real world images -- specifically living things, objects, and human faces -- that people will remember remember via an integration of cognitive models of memory and machine learning techniques. Computer vision models and similarity scaling techniques will be used to produce psychological representations of the images. These representations will then be integrated with cognitive models of memory, which predict that images are more likely to be recognized if they are similar to each of the representations in memory. Large scale memory and similarity rating datasets will be used to develop and test the model.Read moreRead less
Constructing social hierarchy. This project aims to generate new philosophical tools for understanding the persistence of social injustice. It will integrate anti-individualist approaches to mind, language, and action explanation in order to better understand the ways in which social hierarchies are created and maintained, often as the unintended outcome of the actions of multiple agents. The project will enrich the public discussion of hate speech, Indigenous/Non-Indigenous relations, and gende ....Constructing social hierarchy. This project aims to generate new philosophical tools for understanding the persistence of social injustice. It will integrate anti-individualist approaches to mind, language, and action explanation in order to better understand the ways in which social hierarchies are created and maintained, often as the unintended outcome of the actions of multiple agents. The project will enrich the public discussion of hate speech, Indigenous/Non-Indigenous relations, and gender equality.Read moreRead less
The neurobiology of curiosity. This project aims to define the neurobiology of curiosity by combining cutting-edge techniques in computational modelling, pharmacointervention and neuroimaging. It is expected to lead to a comprehensive neuroscientific framework of curiosity, which will characterise its evolution over the lifespan, and its dependency on key neurotransmitter systems. Expected outcomes include a legacy of open access stimulus & data sets; the development of a global collaborative ne ....The neurobiology of curiosity. This project aims to define the neurobiology of curiosity by combining cutting-edge techniques in computational modelling, pharmacointervention and neuroimaging. It is expected to lead to a comprehensive neuroscientific framework of curiosity, which will characterise its evolution over the lifespan, and its dependency on key neurotransmitter systems. Expected outcomes include a legacy of open access stimulus & data sets; the development of a global collaborative network; and an increase in our national capacity and profile in decision neuroscience. The benefits of this project include laying the foundations for future interventions to improve curiosity, with potential downstream effects on many aspects of education, social & public policy.Read moreRead less
Bridging the meaning gap: A computational approach to semantic variation. This project aims to create and validate a new class of large language models that capture and partially explain semantic variation between people. We will (1) measure nuanced differences in word meaning and linguistic experience across individuals; (2) develop computational models that incorporate this variation; and (3) evaluate the extent to which the models capture behavioural and cognitive differences related to polit ....Bridging the meaning gap: A computational approach to semantic variation. This project aims to create and validate a new class of large language models that capture and partially explain semantic variation between people. We will (1) measure nuanced differences in word meaning and linguistic experience across individuals; (2) develop computational models that incorporate this variation; and (3) evaluate the extent to which the models capture behavioural and cognitive differences related to political affiliation, gender, and culture. This will advance our understanding of the nature and origin of individual differences as well as improve the calibration of AI systems for under-represented groups. These advances will support eventual applied outcomes in health, domestic security, and resilience to misinformation. Read moreRead less
Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models ....Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models, based on the incorporation of an explicit searchable memory, which will dramatically reduce model size, hardware requirements and energy usage. This will make modern natural language processing more accessible, while also providing greater flexibility, allowing for more adaptable and portable technologies.Read moreRead less
Categorisation, communication and the local environment. Languages around the world incorporate different systems of categories, and understanding this variation can contribute to a better understanding of similarities and differences between cultures. This project examines how linguistic variation is shaped in part by variation in the local physical and social environment. The methods include computational analyses of large electronic data sets including dictionaries and linguistic corpora tha ....Categorisation, communication and the local environment. Languages around the world incorporate different systems of categories, and understanding this variation can contribute to a better understanding of similarities and differences between cultures. This project examines how linguistic variation is shaped in part by variation in the local physical and social environment. The methods include computational analyses of large electronic data sets including dictionaries and linguistic corpora that have become available only recently, and psychological experiments that probe the causal mechanisms that lead to variation across languages. The outcomes include computational tools that pick out key differences between languages and therefore support cross-cultural communication.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
Self-supervised feature learning for rapid processing of marine imagery. Fast and reliable quantitative estimates of marine environmental health are needed for scientific studies, design and management of protected areas, and regulatory compliance of industrial activity in the ocean. Australia is collecting seafloor images at increasing rates but expert annotations are not keeping up, meaning that typical machine learning approaches struggle. This project will develop self-supervised techniques ....Self-supervised feature learning for rapid processing of marine imagery. Fast and reliable quantitative estimates of marine environmental health are needed for scientific studies, design and management of protected areas, and regulatory compliance of industrial activity in the ocean. Australia is collecting seafloor images at increasing rates but expert annotations are not keeping up, meaning that typical machine learning approaches struggle. This project will develop self-supervised techniques that use large amounts of unlabeled data to enhance performance. Our design takes advantage of additional information available for marine imagery such as geolocation and remote sensing context. We will explore how these representations can guide additional sampling and improve performance in classification tasks.Read moreRead less
Special Research Initiatives - Grant ID: SR200200350
Funder
Australian Research Council
Funding Amount
$282,726.00
Summary
Metaphors and identities in the Australian vernacular. This project investigates the uniqueness of Australian vernacular English from the late 1800s until today. This is an area of vocabulary which most people find fascinating, and yet its formal study has been largely ignored. The project expects to develop a new understanding of Australia’s novel, often entertaining, use of words. Expected project outcomes include a better appreciation of Australian culture and identity, and by employing a new ....Metaphors and identities in the Australian vernacular. This project investigates the uniqueness of Australian vernacular English from the late 1800s until today. This is an area of vocabulary which most people find fascinating, and yet its formal study has been largely ignored. The project expects to develop a new understanding of Australia’s novel, often entertaining, use of words. Expected project outcomes include a better appreciation of Australian culture and identity, and by employing a new interdisciplinary approach. Benefits of the project include the development of podcasts, educational materials, and publications aimed at building an increased awareness of Australian English and its reflection of Australian culture and values. Read moreRead less
Visual evidence: transforming modern sex research (1880s - 1930s). This project aims to explore how photography and film transformed understandings of human sexuality. By analysing how and why doctors and scientists shifted their attention from textual to visual evidence, the project will contribute to understandings about how images have been used historically to create medical norms and communicate scientific knowledge to broad audiences. Focusing on Germany as the international centre of earl ....Visual evidence: transforming modern sex research (1880s - 1930s). This project aims to explore how photography and film transformed understandings of human sexuality. By analysing how and why doctors and scientists shifted their attention from textual to visual evidence, the project will contribute to understandings about how images have been used historically to create medical norms and communicate scientific knowledge to broad audiences. Focusing on Germany as the international centre of early twentieth-century sex research, the project will examine how the turn to visual evidence had a transnational impact by paving the way for post-war researchers such as Kinsey, Masters and Johnson, and for a better understanding of the history of human sexuality in Australia.Read moreRead less