Deep Learning Architecture with Context Adaptive Features for Image Parsing. This project aims to develop a novel deep learning network architecture with contextual adaptive features for image parsing that can improve the object detection accuracy in real-world applications. A number of innovative methods for deep learning, contextual features and network parameter selection will be developed and investigated. The impact of the proposed architecture and features will be improved object-detection ....Deep Learning Architecture with Context Adaptive Features for Image Parsing. This project aims to develop a novel deep learning network architecture with contextual adaptive features for image parsing that can improve the object detection accuracy in real-world applications. A number of innovative methods for deep learning, contextual features and network parameter selection will be developed and investigated. The impact of the proposed architecture and features will be improved object-detection accuracy and advances in deep learning network architecture for image parsing. The intended outcomes are deep learning network architecture, contextual feature extraction techniques and network parameter optimisation techniques for image parsing.Read moreRead less
A Novel Automatic Neural Network Feature Extractor. This project aims to study feature extraction abilities of convolutional as well as traditional neural networks and develop a generic feature extractor which can be applied to wide variety of real-world image and non-image data. New concepts for automatic feature extraction, feature explanation, hybrid evolutionary algorithms and non-iterative ensemble learning will be introduced and evaluated. The expected outcomes are a generic feature extrac ....A Novel Automatic Neural Network Feature Extractor. This project aims to study feature extraction abilities of convolutional as well as traditional neural networks and develop a generic feature extractor which can be applied to wide variety of real-world image and non-image data. New concepts for automatic feature extraction, feature explanation, hybrid evolutionary algorithms and non-iterative ensemble learning will be introduced and evaluated. The expected outcomes are a generic feature extractor for automatically extracting features, an optimiser for finding optimal parameters and non-iterative ensemble learning technique for classification of features into classes. The impact of this project will be automatic feature extractors and classifiers for real-world applications.Read moreRead less
Understanding biological pathways underlying social behaviour in humans. This project aims to show for the first time how oxytocin interacts with neural social and reward pathways to guide social behaviour. Oxytocin is a natural neuropeptide and hormone that has a critical role in the regulation of social behaviour across mammalian species. In animals, direct evidence demonstrates how endogenous and exogenous oxytocin interacts with social and reward neural pathways to alter social behaviour, in ....Understanding biological pathways underlying social behaviour in humans. This project aims to show for the first time how oxytocin interacts with neural social and reward pathways to guide social behaviour. Oxytocin is a natural neuropeptide and hormone that has a critical role in the regulation of social behaviour across mammalian species. In animals, direct evidence demonstrates how endogenous and exogenous oxytocin interacts with social and reward neural pathways to alter social behaviour, including social recognition, relationship formation, and long-term bonds. The project intends to use radio-labelling techniques in combination with positron emission tomography to track oxytocin and show what regions of the brain oxytocin impacts to then influence social cognition and behaviour in humans.Read moreRead less
Attention vs Perception: When is selection optimal, when relational? This project aims to investigate an important, newly discovered dissociation between early visual selection and perceptual decision-making. Contrary to current theories, attentional and perceptual processes are tuned to different stimulus attributes described in the relational vs. optimal account, which implies that current theories of attention do not describe early attention but later, decisional processes. This project will ....Attention vs Perception: When is selection optimal, when relational? This project aims to investigate an important, newly discovered dissociation between early visual selection and perceptual decision-making. Contrary to current theories, attentional and perceptual processes are tuned to different stimulus attributes described in the relational vs. optimal account, which implies that current theories of attention do not describe early attention but later, decisional processes. This project will provide an accurate description of these processes, which promises important theoretical breakthroughs. Work on this project will also significantly advance methods to detect and describe early attentional processes, by identifying error-prone methods of Psychophysics and Neuroscience studies, and proposing remedies.Read moreRead less
Fundamental neurocognitive mechanisms underpinning creative thought. The project aims to understand the neural and cognitive bases of creative thought by using a novel approach and recent framework that has emerged from the study of semantic cognition and executive control functions. Creative thought is fundamental to human advances throughout history and it is the foundation to all arts and sciences. Expected outcomes are a framework that can explain the source of knowledge and the evaluative ....Fundamental neurocognitive mechanisms underpinning creative thought. The project aims to understand the neural and cognitive bases of creative thought by using a novel approach and recent framework that has emerged from the study of semantic cognition and executive control functions. Creative thought is fundamental to human advances throughout history and it is the foundation to all arts and sciences. Expected outcomes are a framework that can explain the source of knowledge and the evaluative mechanisms needed to generate new and useful ideas. Significant benefits will be to advance our understanding of the neurocognitive mechanisms of creative thought, which can enhance Australia’s scientific capability through training and collaboration and broader society by enhancing capacity for innovative thinking. Read moreRead less
Two-way Auslan: Automatic Machine Translation of Australian Sign Language. This project aims to develop an automatic two-way machine-translation system between Auslan (Australian Sign Language) and English by researching and leveraging advanced computer vision and machine learning technology. The project expects to advance research in AI technology on topics including visual recognition, language processing and deep learning. This will boost Australia's national research capacity and global com ....Two-way Auslan: Automatic Machine Translation of Australian Sign Language. This project aims to develop an automatic two-way machine-translation system between Auslan (Australian Sign Language) and English by researching and leveraging advanced computer vision and machine learning technology. The project expects to advance research in AI technology on topics including visual recognition, language processing and deep learning. This will boost Australia's national research capacity and global competitiveness. Expected outcomes of this project will help to break the communication barriers between the Deaf and hearing population. This should provide significant benefits to Deaf communities through enhanced communication and improved quality-of-life, leading to a fair, more inclusive and resilient Australian society.Read moreRead less
Investigating differences in decision-making ability in older adults. This project aims to investigate how healthy ageing impacts decision making and its associated neural circuits using computation modelling and neurogenetic methods. Decision-making is a fundamental cognitive ability, allowing us to choose the best course of action. This project will investigate the relationship between genes and decision-making performance across the adult lifespan. Expected outcomes include a deeper understan ....Investigating differences in decision-making ability in older adults. This project aims to investigate how healthy ageing impacts decision making and its associated neural circuits using computation modelling and neurogenetic methods. Decision-making is a fundamental cognitive ability, allowing us to choose the best course of action. This project will investigate the relationship between genes and decision-making performance across the adult lifespan. Expected outcomes include a deeper understanding of how decision-making evolves in healthy ageing, and a tool based on genetic scores and computational modelling to predict an individual's trajectory of cognitive function. This could help identify individuals who are at risk for cognitive decline, which could then inform better interventions.Read moreRead less
Dynamic DNA structure states and memory formation. Activity-induced gene expression is central to neural plasticity, learning, and memory; however, the underlying mechanisms of these processes in the brain have yet to be fully resolved. The aim of this proposal is to obtain a deeper understanding of the functional relationship between genes and brain function. By elucidating the full repertoire of epigenetic mechanisms in the brain during learning and the formation of memory, it is hoped that t .... Dynamic DNA structure states and memory formation. Activity-induced gene expression is central to neural plasticity, learning, and memory; however, the underlying mechanisms of these processes in the brain have yet to be fully resolved. The aim of this proposal is to obtain a deeper understanding of the functional relationship between genes and brain function. By elucidating the full repertoire of epigenetic mechanisms in the brain during learning and the formation of memory, it is hoped that the true nature of brain adaptation across the lifespan will be revealed. Findings which may then provide new opportunities to strengthen, maintain and optimise cognitive function.Read moreRead less
Australian Laureate Fellowships - Grant ID: FL210100045
Funder
Australian Research Council
Funding Amount
$3,245,263.00
Summary
Energy-efficient artificial intelligence using quantum technologies. Artificial intelligence (AI) is transforming society but standard technologies come with significant hidden costs: training even a single, common, learning model can emit 5 times more carbon dioxide than the lifetime emissions of the average car. This Fellowship aims to develop artificial intelligence platforms using Australia’s significant investment in quantum technologies to bypass traditional approaches to AI. The expected ....Energy-efficient artificial intelligence using quantum technologies. Artificial intelligence (AI) is transforming society but standard technologies come with significant hidden costs: training even a single, common, learning model can emit 5 times more carbon dioxide than the lifetime emissions of the average car. This Fellowship aims to develop artificial intelligence platforms using Australia’s significant investment in quantum technologies to bypass traditional approaches to AI. The expected outcomes are neuromorphic computers that operate efficiently—with low-energy cost—and rapidly—achieving speeds impossible with conventional electronic approaches. The anticipated benefits are transformative technologies for AI, new applications across society, and new tools for exploring brain function and cognition.Read moreRead less