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
Detecting and tracking alertness using speech biometrics. Traditional tests for detecting and tracking alertness are limited by their accuracy and inability to be administered without stopping work. This project aims to investigate how speech can be used to monitor changes in performance resulting from sleep deprivation and successive night shifts. The expected outcomes are 1) new knowledge on how sensitive speech and language features are for detecting change in alertness, and 2) development an ....Detecting and tracking alertness using speech biometrics. Traditional tests for detecting and tracking alertness are limited by their accuracy and inability to be administered without stopping work. This project aims to investigate how speech can be used to monitor changes in performance resulting from sleep deprivation and successive night shifts. The expected outcomes are 1) new knowledge on how sensitive speech and language features are for detecting change in alertness, and 2) development and verification of a highly accurate, cost-effective, speech focussed assay capable of detecting impaired alertness from otherwise healthy individuals. The project should benefit the way fitness for duty is tested and provide new methods for safeguarding Australians working in at-risk environments.Read moreRead less
Fairness in Natural Language Processing. Natural language processing (NLP) has achieved spectacular commercial successes in recent years, and has been deployed across an ever-increasing breadth of devices and application areas. At the same time, there has been stark evidence to indicate that naively-trained models amplify biases in training data, and perform inconsistently across text relating to different demographic groupings of individuals. This project aims to systematically quantify the ext ....Fairness in Natural Language Processing. Natural language processing (NLP) has achieved spectacular commercial successes in recent years, and has been deployed across an ever-increasing breadth of devices and application areas. At the same time, there has been stark evidence to indicate that naively-trained models amplify biases in training data, and perform inconsistently across text relating to different demographic groupings of individuals. This project aims to systematically quantify the extent of such biases, and develop models that are both more socially equitable, as well as less prone to expose private data in the learned representations. In doing so, it will make NLP more accessible to new populations of users, and remove socio-technological barriers to NLP uptake.Read moreRead less
Multi-Modal Dictionary Learning for Smart City Operation and Management. This Project aims to provide new digital asset management tools for city councils to improve city services by utilising new sensing and automated learning technologies for recognising, tracking and auditing of assets. Currently, there are no digital tools available to handle these services. This project proposes new multi-modal sensing and mapping of city asset techniques by building new multi-modal dictionary learning proc ....Multi-Modal Dictionary Learning for Smart City Operation and Management. This Project aims to provide new digital asset management tools for city councils to improve city services by utilising new sensing and automated learning technologies for recognising, tracking and auditing of assets. Currently, there are no digital tools available to handle these services. This project proposes new multi-modal sensing and mapping of city asset techniques by building new multi-modal dictionary learning procedures. The new framework will recognise different conditions of city assets in real-time to make decisions. Expected outcomes of this Project include integration and easy access of assets with unique digital identities to help city councils, governments, and navigation services for real-time asset monitoring.Read moreRead less
Nurturing Australia's Little Multilingual Minds. Despite its substantial multilingual capacity of more than 300 languages, Australia has been described as a 'graveyard for languages'. In partnering with community organisations we will facilitate polyglot early learning, commencing with Spanish and Vietnamese. Expected outcomes are a deep understanding of multilingual families’ experiences, a model to support lifespan multilingual education, and openly-accessible database of child language in her ....Nurturing Australia's Little Multilingual Minds. Despite its substantial multilingual capacity of more than 300 languages, Australia has been described as a 'graveyard for languages'. In partnering with community organisations we will facilitate polyglot early learning, commencing with Spanish and Vietnamese. Expected outcomes are a deep understanding of multilingual families’ experiences, a model to support lifespan multilingual education, and openly-accessible database of child language in heritage languages. Benefits include a pivotal contribution to early childhood education with the creation of a tailor-made, principle-based program, which will enhance children’s academic achievement, familial social and mental wellbeing, and cultural and economic opportunities for all Australians. Read moreRead less
Using visual science to reduce the dangers of night driving. This project aims to develop novel tests of visual function relevant to the modern night driving environment. Night driving is challenging for all drivers and has been linked to poor visibility under low light conditions. This project will characterise the visual challenges of the modern night driving environment, develop visual tests that incorporate the dynamic light levels typical of night-time roads and assess the association of th ....Using visual science to reduce the dangers of night driving. This project aims to develop novel tests of visual function relevant to the modern night driving environment. Night driving is challenging for all drivers and has been linked to poor visibility under low light conditions. This project will characterise the visual challenges of the modern night driving environment, develop visual tests that incorporate the dynamic light levels typical of night-time roads and assess the association of these tests with night driving performance. The outcomes will contribute new knowledge regarding dynamic visual processing and the ageing visual system and will inform vision testing, potential interventions to improve visual function for night driving and reduce the dangers of night driving.Read moreRead less
Robust, valid and interpretable deep learning for quantitative imaging. One of the biggest challenges in employing artificial intelligence is the “black-box” nature of the models used. This project aims to improve the effectiveness and trustworthiness of deep learning within quantitative magnetic resonance imaging. Deep learning has great promise in speeding-up complex image processing tasks, but currently suffers from variable data inputs, predictions are not guaranteed to be plausible and it i ....Robust, valid and interpretable deep learning for quantitative imaging. One of the biggest challenges in employing artificial intelligence is the “black-box” nature of the models used. This project aims to improve the effectiveness and trustworthiness of deep learning within quantitative magnetic resonance imaging. Deep learning has great promise in speeding-up complex image processing tasks, but currently suffers from variable data inputs, predictions are not guaranteed to be plausible and it is not clear to the end user how reliable the results are. The outcomes intend to deliver advanced knowledge and capability in artificial intelligence and machine learning that Australia urgently needs to capitalise on bringing deep learning into practical applications delivering economic, commercial and social impact.Read moreRead less
Central Representation of Electroacoustic Stimuli. Cochlear implantation, initially only provided to profoundly deaf individuals, is now routine in people with substantial residual hearing. Although stimulation via a cochlear implant and hearing aid in the same ear has been shown to improve speech understanding, particularly in noise, and to increase the aesthetic quality of sound, almost nothing is known about the physiological mechanisms underlying these benefits. The broad aim of our project ....Central Representation of Electroacoustic Stimuli. Cochlear implantation, initially only provided to profoundly deaf individuals, is now routine in people with substantial residual hearing. Although stimulation via a cochlear implant and hearing aid in the same ear has been shown to improve speech understanding, particularly in noise, and to increase the aesthetic quality of sound, almost nothing is known about the physiological mechanisms underlying these benefits. The broad aim of our project is to address this deficiency by measuring the patterns of neural activity evoked by speech sounds across the tonotopic axis in the inferior colliculus and auditory cortex and assess the extent to which the pattern of neural activity allows discrimination between the different speech sounds.Read moreRead less
Novel mechanisms for regulating the retinal vasculature. Tight control of the retinal vasculature is crucial for maintaining normal vision. Unlike most blood vessels in the body, those in the retina and brain receive no direct neural control. Rather they rely on support cells to communicate the needs of neurons. This project aims to examine the mechanisms by which resident immune cells, called microglia, regulate retinal capillaries in response to neural activity. New knowledge examining a novel ....Novel mechanisms for regulating the retinal vasculature. Tight control of the retinal vasculature is crucial for maintaining normal vision. Unlike most blood vessels in the body, those in the retina and brain receive no direct neural control. Rather they rely on support cells to communicate the needs of neurons. This project aims to examine the mechanisms by which resident immune cells, called microglia, regulate retinal capillaries in response to neural activity. New knowledge examining a novel mechanism will be generated. This information is crucial for enhancing our understanding of how blood vessels are controlled in the retina and brain and will guide the development of novel ways of examining blood vessel function.Read moreRead less