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
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
Spatial Cognition—Expressive Representation Formalisms and Effective Reasoning Mechanisms. The project will contribute significantly to the advancement of knowledge in breakthrough science in qualitative spatial reasoning and smart information use in geographic information systems. Expressive spatial languages are important in organising spatial knowledge, defining spatial query languages and guiding spatial data mining. Effective spatial reasoning mechanisms bring theory closer to applications ....Spatial Cognition—Expressive Representation Formalisms and Effective Reasoning Mechanisms. The project will contribute significantly to the advancement of knowledge in breakthrough science in qualitative spatial reasoning and smart information use in geographic information systems. Expressive spatial languages are important in organising spatial knowledge, defining spatial query languages and guiding spatial data mining. Effective spatial reasoning mechanisms bring theory closer to applications including consistency checking and spatial query pre-processing. The project will help in extracting knowledge from massive spatial databases, meeting the growing needs of naive users for spatial information and establishing Australia as a major player in spatial cognition research and in the development of geo-location services.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE210100749
Funder
Australian Research Council
Funding Amount
$434,030.00
Summary
Machine learning of subgrid ocean physics for global ocean models. Climate projections require simulations with ocean-climate models for hundreds of years. Computational resources limit the resolution of our models for such long runs, meaning that some key physical processes remain unresolved and must be parameterised. This project uses machine learning to find new parameterisations for unresolved ocean processes. These new parameterisations will be implemented into computationally cheaper coars ....Machine learning of subgrid ocean physics for global ocean models. Climate projections require simulations with ocean-climate models for hundreds of years. Computational resources limit the resolution of our models for such long runs, meaning that some key physical processes remain unresolved and must be parameterised. This project uses machine learning to find new parameterisations for unresolved ocean processes. These new parameterisations will be implemented into computationally cheaper coarse-resolution ocean models, thereby enhancing these models' representation of the ocean circulation. This project expects to reveal the dynamics of unresolved processes, to improve the accuracy of climate projections and to provide a proof-of-concept for how machine learning can be used in ocean and climate science.Read moreRead less
Foundations and Architectures for Agent Systems. Computer systems are now involved in many aspects of everyday life, commerce, and industry. Making these systems more intelligent has thus become a priority research issue. Agents systems, with their emphasis on autonomy, proactiveness, reactivity, and sociability, are widely regarded as a crucial technology for realising the capabilities that computer systems will need over the next few decades. The proposed research aims to make some fundamenta ....Foundations and Architectures for Agent Systems. Computer systems are now involved in many aspects of everyday life, commerce, and industry. Making these systems more intelligent has thus become a priority research issue. Agents systems, with their emphasis on autonomy, proactiveness, reactivity, and sociability, are widely regarded as a crucial technology for realising the capabilities that computer systems will need over the next few decades. The proposed research aims to make some fundamental contributions to agent systems that will be used to build future computer systems that will have an even more profound positive impact on everyday life, commerce and industry than existing systems.Read moreRead less
3D Vision Geometric Optimisation in Deep Learning. This project aims to develop a methodology for integrating the algorithms of 3D Vision Geometry and Optimization into the framework of Machine Learning and demonstrate the wide applicability of the new methods on a variety of challenging fundamental problems in Computer Vision. These include 3D geometric scene understanding, and estimation and prediction of human 2D/3D pose and activity. Applications of this technology are to be found in Intell ....3D Vision Geometric Optimisation in Deep Learning. This project aims to develop a methodology for integrating the algorithms of 3D Vision Geometry and Optimization into the framework of Machine Learning and demonstrate the wide applicability of the new methods on a variety of challenging fundamental problems in Computer Vision. These include 3D geometric scene understanding, and estimation and prediction of human 2D/3D pose and activity. Applications of this technology are to be found in Intelligent Transportation, Environment Monitoring, and Augmented Reality, applicable in smart-city planning and medical applications such as computer-enhanced surgery. The goal is to build Australia's competitive advantage in the forefront of ICT research and technology innovation.Read moreRead less
Network Intrusion Detection via Machine Learning. Computer security is an increasingly important, yet complex task. It
takes significant skills to configure systems properly such that they
are safe from malicious attacks.
The proposed project aims at designing automatic systems which are
able to adapt to an existing network configuration and which detect
novel and unusual events. For this purpose we will use modern machine
learning techniques, mainly based on kernels. In particular, rec ....Network Intrusion Detection via Machine Learning. Computer security is an increasingly important, yet complex task. It
takes significant skills to configure systems properly such that they
are safe from malicious attacks.
The proposed project aims at designing automatic systems which are
able to adapt to an existing network configuration and which detect
novel and unusual events. For this purpose we will use modern machine
learning techniques, mainly based on kernels. In particular, recently
developed algorithms to estimate the support of a distribution and
detect rare events will be employed in this context.
The project is in cooperation with Dr. Ralf Herbrich (Microsoft
Research, Cambridge).
Read moreRead less
Design surface feature recognition for near net shaped manufactured components. The aim of this project is to investigate methods and techniques that, given an ab initio design requirement, allow databases of knowledge from previous designs to be intelligently searched for similar patterns, both geometric and physical state, that will assess the likelihood of a successful design and suggest potential alternatives based on previous experience
The plan is to approach the research problem from a m ....Design surface feature recognition for near net shaped manufactured components. The aim of this project is to investigate methods and techniques that, given an ab initio design requirement, allow databases of knowledge from previous designs to be intelligently searched for similar patterns, both geometric and physical state, that will assess the likelihood of a successful design and suggest potential alternatives based on previous experience
The plan is to approach the research problem from a machine learning/pattern recognition point of view. By mapping the characterized properties into a search space of reduced dimensionality in which feature patterns have been pre-classified through supervised training, it should be possible to identify similar features.
Read moreRead less
Computer Vision Optimization Problems Using Machine Learning. Computer Vision concerns itself with understanding the world through the analysis of images obtained by a video or still camera. An important application is tracking of people in video and modelling their movements. This has evident applications in security, sport and entertainment. By enabling the computer to capture the motion of a subject in a video, we may detect suspicious activity in security, analyze the motion (golf-swing, ....Computer Vision Optimization Problems Using Machine Learning. Computer Vision concerns itself with understanding the world through the analysis of images obtained by a video or still camera. An important application is tracking of people in video and modelling their movements. This has evident applications in security, sport and entertainment. By enabling the computer to capture the motion of a subject in a video, we may detect suspicious activity in security, analyze the motion (golf-swing, diving style) of a sports-person, or capture the motion of an actor for animation or game applications. Development of a reliable technology requires new optimization techniques, which will place Australia at the forefront of the application of such research, commercially and for the public benefit.Read moreRead less
Industrial Transformation Training Centres - Grant ID: IC190100031
Funder
Australian Research Council
Funding Amount
$3,973,202.00
Summary
ARC Training Centre in Data Analytics for Resources and Environments (DARE). Understanding the cumulative impact of actions regarding the use of our resources has important long-term consequences for Australia’s economic, societal and environmental health. Yet despite the importance of these cumulative impacts, and the availability of data, many decisions and policies are based on limited amounts of data and rudimentary data analysis, with little appreciation of the critical role that understand ....ARC Training Centre in Data Analytics for Resources and Environments (DARE). Understanding the cumulative impact of actions regarding the use of our resources has important long-term consequences for Australia’s economic, societal and environmental health. Yet despite the importance of these cumulative impacts, and the availability of data, many decisions and policies are based on limited amounts of data and rudimentary data analysis, with little appreciation of the critical role that understanding and quantifying uncertainty plays in the process. The aim of Data Analytics in Resources and Environment (DARE) is to develop and deliver the data science skills and tools for Australia’s resource industries to make the best possible evidence-based decisions in exploiting and stewarding the nation’s natural resources.Read moreRead less