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
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
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
Toward Human-guided Safe Reinforcement Learning in the Real World. This project aims to investigate human-guided safe reinforcement learning (RL). Safe RL is an important topic that could enable real applications of RL systems by addressing safety constraints. Existing safe RL assumes the availability of specified safety constraints in mathematical or logical forms. This project proposes to study learning safety objectives from information provided directly by humans or indirectly via language m ....Toward Human-guided Safe Reinforcement Learning in the Real World. This project aims to investigate human-guided safe reinforcement learning (RL). Safe RL is an important topic that could enable real applications of RL systems by addressing safety constraints. Existing safe RL assumes the availability of specified safety constraints in mathematical or logical forms. This project proposes to study learning safety objectives from information provided directly by humans or indirectly via language models, and human-guided continuous correction for safety improvements. The established theories and developed algorithms will advance frontier technologies in AI and contribute to a wide range of real applications of safe RL, such as robotics and autonomous driving, bringing enormous social and economic benefits. Read moreRead less
Deep Adder Networks on Edge Devices. This project aims to empower edge devices with intelligence by developing advanced deep neural networks that address the conflict between the high resource requirements of deep learning and the generally inadequate performance of the edge. Multiplication has been the dominant type of operation in deep learning, though the addition is known to be much cheaper. This project expects to yield theories and algorithms that allow deep neural networks consisting of n ....Deep Adder Networks on Edge Devices. This project aims to empower edge devices with intelligence by developing advanced deep neural networks that address the conflict between the high resource requirements of deep learning and the generally inadequate performance of the edge. Multiplication has been the dominant type of operation in deep learning, though the addition is known to be much cheaper. This project expects to yield theories and algorithms that allow deep neural networks consisting of nearly pure additions to fulfil the requisites of accuracy, robustness, calibration and generalisation in real-world computer vision tasks. The success of this project will benefit deep learning-based products on smartphones or robots in health and cybersecurity.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE230101591
Funder
Australian Research Council
Funding Amount
$419,154.00
Summary
Towards Real-world Continual Learning on Unrestricted Task Steams. This project aims to enable machines to continually learn without forgetting and accumulate knowledge from the sequential data streams containing diverse tasks. This project expects to advance the continual learning to unrestricted real-world task steams that are long-term and complex and promote artificial intelligence toward the human-level intelligence that can automatically evolve during interaction with the world. Expected o ....Towards Real-world Continual Learning on Unrestricted Task Steams. This project aims to enable machines to continually learn without forgetting and accumulate knowledge from the sequential data streams containing diverse tasks. This project expects to advance the continual learning to unrestricted real-world task steams that are long-term and complex and promote artificial intelligence toward the human-level intelligence that can automatically evolve during interaction with the world. Expected outcomes of this project include the paradigm-shifting continual learning framework and techniques for handling unrestricted task steams in real-world scenarios. They will benefit society and the economy nationally and internationally by enhancing the applicability of artificial intelligence.Read moreRead less
Generative Visual Pre-training on Unlabelled Big Data. This project aims to develop a generative visual pre-training of large-scale deep neural networks on unlabelled big data. Developing pre-trained visual models that are accurate, robust, and efficient for downstream tasks is a keystone of modern computer vision, but it poses challenges and knowledge gaps to existing unsupervised representation learning. Expected outcomes include new theories and algorithms for unsupervised visual pre-training ....Generative Visual Pre-training on Unlabelled Big Data. This project aims to develop a generative visual pre-training of large-scale deep neural networks on unlabelled big data. Developing pre-trained visual models that are accurate, robust, and efficient for downstream tasks is a keystone of modern computer vision, but it poses challenges and knowledge gaps to existing unsupervised representation learning. Expected outcomes include new theories and algorithms for unsupervised visual pre-training, which are anticipated to deepen our understanding of visual representation and make it easier to build and deploy computer vision applications and services. Examples of benefits include modernising machines in manufacturing and farming with visual intelligence. 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
Exploiting Geometries of Learning for Fast, Adaptive and Robust AI. This project aims to uniquely exploit geometric manifolds in deep learning to advance the frontier of Artificial Intelligence (AI) research and applications in cybersecurity and general cognitive tasks. It expects to develop new theories, algorithms, tools, and technologies for machine learning systems that are fast, adaptive, lifelong and robust, even with limited supervision. Expected outcomes will enhance Australia's capabili ....Exploiting Geometries of Learning for Fast, Adaptive and Robust AI. This project aims to uniquely exploit geometric manifolds in deep learning to advance the frontier of Artificial Intelligence (AI) research and applications in cybersecurity and general cognitive tasks. It expects to develop new theories, algorithms, tools, and technologies for machine learning systems that are fast, adaptive, lifelong and robust, even with limited supervision. Expected outcomes will enhance Australia's capability and competitiveness in AI, and deliver robust and trustworthy learning technology. The project should provide significant benefits not only in advancing scientific and translational knowledge but also in accelerating AI innovations, safeguarding cyberspace, and reducing the burden on defence expenses in Australia.Read moreRead less