Pattern Recognition and Scene Analysis via Machine Learning. We plan to use kernel methods, a novel machine learning technique, for computer vision problems, such as scene analysis and real time object recognition. Such capabilities are relevant for the design of intelligent and adaptive systems, suitable for complex real world environments. Expected outcomes are the design of efficient statistical tools which take the special nature of visual data into account (structure, decomposition, prior ....Pattern Recognition and Scene Analysis via Machine Learning. We plan to use kernel methods, a novel machine learning technique, for computer vision problems, such as scene analysis and real time object recognition. Such capabilities are relevant for the design of intelligent and adaptive systems, suitable for complex real world environments. Expected outcomes are the design of efficient statistical tools which take the special nature of visual data into account (structure, decomposition, prior knowledge of physical environments, etc.) and combine the advantages of feature based high-level vision methods with low-level machine learning techniques.
This proposal is part of a joint IST project with partners from the European Union.Read moreRead less
Parallel and Distributed Machine Learning - Smart Data Analysis in the Multicore Era. In large data centres our research will lead to reduced energy consumption by using graphics cards which have a much better computation to power ratio than traditional processors. On desktop computers, it will make machine learning practical by enabling efficient algorithms for spam filtering and content analysis. On networked systems it will lead to distributed inference, caching and collaborative filtering ap ....Parallel and Distributed Machine Learning - Smart Data Analysis in the Multicore Era. In large data centres our research will lead to reduced energy consumption by using graphics cards which have a much better computation to power ratio than traditional processors. On desktop computers, it will make machine learning practical by enabling efficient algorithms for spam filtering and content analysis. On networked systems it will lead to distributed inference, caching and collaborative filtering applications which will both reduced the bandwidth required and make the internet safer for users. Finally, it will enable rapid deployment of sensor networks for monitoring and detection, such as for environmental monitoring and safeguarding Australia's borders.Read moreRead less
Reconceiving Machine Learning. The proposed research will develop a new way to consider problems to which machine learning can be applied. Machine learning is crucial enabler of the digital economy. The research will provide better opportunities for Australian industry to gain a competitive advantage with machine learning technology. The framework developed will enable better opportunities for collaborative research and will build and strengthen international linkages.
Exploiting Structure in AI Planning. The research will improve our ability to build generic, automated planning systems, which can efficiently select effective courses of actions in a range of situations such as crisis management, project planning, military operations planning, and transportation. It will help reduce the cost of building software to more efficiently solve important problems occurring in validating, controlling, and diagnosing complex systems. More generally, it will advance our ....Exploiting Structure in AI Planning. The research will improve our ability to build generic, automated planning systems, which can efficiently select effective courses of actions in a range of situations such as crisis management, project planning, military operations planning, and transportation. It will help reduce the cost of building software to more efficiently solve important problems occurring in validating, controlling, and diagnosing complex systems. More generally, it will advance our understanding of how machines can intelligently solve complex problems by identifying and exploiting their relevant structure.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
Engineering Artificial Intelligence: A Spatial Representation and Reasoning Perspective. Spatial information is important in areas of national interest such as mining and exploration, environmental monitoring and planning, emergency response, and defence. Mission control centres, for instance, receive different forms of spatial data from satellites, radar, or people on the ground. They have to process the input data and make intelligent decisions in a very limited time. Intelligent systems that ....Engineering Artificial Intelligence: A Spatial Representation and Reasoning Perspective. Spatial information is important in areas of national interest such as mining and exploration, environmental monitoring and planning, emergency response, and defence. Mission control centres, for instance, receive different forms of spatial data from satellites, radar, or people on the ground. They have to process the input data and make intelligent decisions in a very limited time. Intelligent systems that are able to assist with processing different forms of spatial data efficiently and that offer reliable decision support are essential for improving the quality and reliability of such applications. This research enables future intelligent systems with these capabilities. This will directly benefit applications in areas of national interest.Read moreRead less
Where the Really Hard Problems Are: Beyond the Decision Case. This is a project in empirical artificial intelligence. We study factors affecting the average difficulty of computing optimal or near-optimal solutions to instances of problems whose worst cases are typically intractable. Most existing research on the distribution of hard instances concerns decision questions, where the issue is whether solutions exist or not. We seek comparable results for optimization, where the goal is the best so ....Where the Really Hard Problems Are: Beyond the Decision Case. This is a project in empirical artificial intelligence. We study factors affecting the average difficulty of computing optimal or near-optimal solutions to instances of problems whose worst cases are typically intractable. Most existing research on the distribution of hard instances concerns decision questions, where the issue is whether solutions exist or not. We seek comparable results for optimization, where the goal is the best solution, and for approximation, where the goal is a good solution. Expected outcomes include new heuristics for search algorithms, new methods for predicting search costs, and explanations of the average case behaviour of algorithms.Read moreRead less
Structures and Protocols for Inference. The proposed research is expected to lead to increased adoption and efficiency of use of machine learning technologies. It will develop new and better ways to use existing machine learning software in a manner that allows easier integration into commercial products. It will increase the competitiveness of Australian industry.
From Universal Induction to Intelligent Systems. The dream of creating artificial devices that (out)reach human intelligence is an old one. What makes this challenge so interesting? A solution would have enormous implications for our society, and there are arguments that the AI problem might be solved within a couple of decades. Specialized intelligent systems are actually already pervasive (finger print, handwriting, speech, and face recognition; spam filtering; search engines; computer chess; ....From Universal Induction to Intelligent Systems. The dream of creating artificial devices that (out)reach human intelligence is an old one. What makes this challenge so interesting? A solution would have enormous implications for our society, and there are arguments that the AI problem might be solved within a couple of decades. Specialized intelligent systems are actually already pervasive (finger print, handwriting, speech, and face recognition; spam filtering; search engines; computer chess; robots). This decade the first presumably complete mathematical theory of AI has been proposed. By working out this theory, this project will significantly contribute to the foundations of inductive inference and AI, and ultimately lead to smarter software and intelligent systems.Read moreRead less
Kernel and Margin Based Machine Learning Algorithms. Certain machine learning algorithms, such as support vector machines, utilizing
the ideas of large margins and kernels have attracted much attention lately
because of their impressive performance on real world problems such as optical
character recognition. We plan to refine and extend such algorithms to a wide
range of different machine learning problems such as gene sequence analysis,
image processing and text classification. Expected ....Kernel and Margin Based Machine Learning Algorithms. Certain machine learning algorithms, such as support vector machines, utilizing
the ideas of large margins and kernels have attracted much attention lately
because of their impressive performance on real world problems such as optical
character recognition. We plan to refine and extend such algorithms to a wide
range of different machine learning problems such as gene sequence analysis,
image processing and text classification. Expected outcomes include the
development of software that allows the solution of hitherto unsolved machine
learning problems, and the ability to solve problems larger than those solvable
by the current generation of machine learning tools.Read moreRead less