AUSLearn: AUtomated Sample Learning for Object Recognition. This project aims to enable computers to learn how to effectively use training samples for object recognition. Training sample is the only source used by computers to learn recognising objects. This project creates a new research direction that will enable the first full exploration of the power of samples. The aims will be enabled by leveraging the recent advances in reinforcement learning, fast training algorithms, and by developing n ....AUSLearn: AUtomated Sample Learning for Object Recognition. This project aims to enable computers to learn how to effectively use training samples for object recognition. Training sample is the only source used by computers to learn recognising objects. This project creates a new research direction that will enable the first full exploration of the power of samples. The aims will be enabled by leveraging the recent advances in reinforcement learning, fast training algorithms, and by developing novel deep learning algorithms. The new algorithms will benefit a wide range of applications, e.g. to effectively use car crash training samples for accurately identifying potential road crashes in transport and to effectively use rare medical imaging training data for robustly diagnosing diseases in health.Read moreRead less
Sustainable mobility: city-wide exposure modelling to advance bicycling. This project aims to develop a world-leading platform for city-wide modelling of cycling exposure. This project will provide unparalleled insights into cycling exposure by combining multiple cycling data sources through the use of advanced spatial statistical and machine learning techniques. The expected outcomes of this project are a novel inventory of cycling infrastructure, a cycling route choice modelling system and rob ....Sustainable mobility: city-wide exposure modelling to advance bicycling. This project aims to develop a world-leading platform for city-wide modelling of cycling exposure. This project will provide unparalleled insights into cycling exposure by combining multiple cycling data sources through the use of advanced spatial statistical and machine learning techniques. The expected outcomes of this project are a novel inventory of cycling infrastructure, a cycling route choice modelling system and robust predictions of cycling volumes on individual streets. This project will deliver a step change in cycling that will lead to increased cycling participation, enhanced safety, and improved infrastructure planning, thereby resulting in substantial gains in population and environmental health.Read moreRead less