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
Vision Model Based Perceptual Digital Video Coding. Digital video coding and compression is an enabling technology and has diversified applications in audiovisual communications, multimedia computing, digital television broadcast and electronic entertainment industries. The project aims at spearheading research in theory, techniques and implementation of perceptual video coding in order to achieve constant and guaranteed quality in visual communications and services. It will explore a new appr ....Vision Model Based Perceptual Digital Video Coding. Digital video coding and compression is an enabling technology and has diversified applications in audiovisual communications, multimedia computing, digital television broadcast and electronic entertainment industries. The project aims at spearheading research in theory, techniques and implementation of perceptual video coding in order to achieve constant and guaranteed quality in visual communications and services. It will explore a new approach to digital video coding other than the constant bit rate coding techniques which have dominated digital video research for the past four decades. It will form a part of the theoretical foundation and principles for the next generation video coding and compression techniques, and may lead to new standards and practice.Read moreRead less
Ensembles of Collaborative Neural Networks. Artificial neural networks have been used successfully for data mining and control. A neural network ensemble(NNE) is a collection of networks that exhibits properties of self-organization, plasticity, and adaptive behaviour. The aim of this research is to develop an efficient and theoretically sound algorithm for NNE learning. The outcomes of the project will include insights into self-organization of complex NNE and automatic problem decomposition an ....Ensembles of Collaborative Neural Networks. Artificial neural networks have been used successfully for data mining and control. A neural network ensemble(NNE) is a collection of networks that exhibits properties of self-organization, plasticity, and adaptive behaviour. The aim of this research is to develop an efficient and theoretically sound algorithm for NNE learning. The outcomes of the project will include insights into self-organization of complex NNE and automatic problem decomposition and an efficient algorithm for constructing and training NNE. Practical outcomes will include research training for early career researchers and new modelling tools for data mining, robotics and multi-agent systems. The project contributes to the national priority area of smart information use.Read moreRead less
Automatic detection of the circle of Willis in neuro-images using multi-scale gradient calculation and knowledge-based genetic algorithms. Stroke is the third most common cause of death and a major contributor to long term disability in Australia. The most efficient way of preventing stroke from happening is to detect related symptoms early. The group of cerebral blood vessels that closely related to strokes is the circle of Willis (CoW). We build a system that can automatically detect and quan ....Automatic detection of the circle of Willis in neuro-images using multi-scale gradient calculation and knowledge-based genetic algorithms. Stroke is the third most common cause of death and a major contributor to long term disability in Australia. The most efficient way of preventing stroke from happening is to detect related symptoms early. The group of cerebral blood vessels that closely related to strokes is the circle of Willis (CoW). We build a system that can automatically detect and quantify CoW in neuroimages, providing ways of preventing strokes from happening. The project will enhance Australia¡¯s leading position in promoting and maintaining good health, especially in preventive healthcare.Read moreRead less
Developing optimal synthesis strategies in distributed expert systems. The aim of this project is to investigate synthesis strategies in distributed expert systems (DESs). Such strategies are used to synthesize multiple solutions to the same task from different experts (either human experts or expert systerms) in order to obtain the final solution to the task. These strategies could be used in a wide application of domains such as insurance agencies and medical diagnosis systems. The expected ....Developing optimal synthesis strategies in distributed expert systems. The aim of this project is to investigate synthesis strategies in distributed expert systems (DESs). Such strategies are used to synthesize multiple solutions to the same task from different experts (either human experts or expert systerms) in order to obtain the final solution to the task. These strategies could be used in a wide application of domains such as insurance agencies and medical diagnosis systems. The expected outcomes are to develop computational strategies, neural network strategies, and case-based strategies for solving different synthesis cases.Read moreRead less
On-line structural integrity assessment of advanced composite airframe with senor network. The project addresses frontier technologies that lead to solutions to one of the critical key issues forming the Australian community - online integrity/safety assessment of structures or asset including aircraft, ships, buildings and bridges. The community benefits significantly if potential disaster due to occurrence of damage associated with those structures can be prevented - the ultimate aim of resear ....On-line structural integrity assessment of advanced composite airframe with senor network. The project addresses frontier technologies that lead to solutions to one of the critical key issues forming the Australian community - online integrity/safety assessment of structures or asset including aircraft, ships, buildings and bridges. The community benefits significantly if potential disaster due to occurrence of damage associated with those structures can be prevented - the ultimate aim of researchers for decades. It is imperative that Australian industries remain technologically ahead of international competitors. Outcomes of the project will lead to novel technologies for real-time structural health monitoring and integrity assessment, bringing significant improvement in operation safety and driving down maintenance cost.Read moreRead less
Development of an Integrated Platform for Performance-Based Safety Assessment. Building fires are the cause of major fatalities and injuries amongst all types of accidental fires in Australia. With significant advancement in numerical simulation technique, computer models are becoming acceptable tools for fire safety designs. Nonetheless, these methods still suffer from large amount of manual inputs and lengthy computational times. This research project will address the prevalent deficiency in m ....Development of an Integrated Platform for Performance-Based Safety Assessment. Building fires are the cause of major fatalities and injuries amongst all types of accidental fires in Australia. With significant advancement in numerical simulation technique, computer models are becoming acceptable tools for fire safety designs. Nonetheless, these methods still suffer from large amount of manual inputs and lengthy computational times. This research project will address the prevalent deficiency in many of these computer models and develop a novel and innovative design methodology. The success of this project will revolutionize the computational tools for the industry realizing a convenient, robust and time-saving integrated platform catering for increasing future market demand.Read moreRead less
Analysing Iterative Machine Learning Algorithms with Information Geometric Methods. Online machine learning problems arise from situations where data is provided a point at a time. There are many classical algorithms for solving such problems based on the principle of stochastic gradient descent. Recent research by the CIs and others have thrown up interesting but diverse geometric connections that offer new insights. The proposed research aims to integrate the understanding of these algori ....Analysing Iterative Machine Learning Algorithms with Information Geometric Methods. Online machine learning problems arise from situations where data is provided a point at a time. There are many classical algorithms for solving such problems based on the principle of stochastic gradient descent. Recent research by the CIs and others have thrown up interesting but diverse geometric connections that offer new insights. The proposed research aims to integrate the understanding of these algorithms with the aim of designing algorithms better able to exploit prior knowledge, and to extend existing algorithms to new problem domains thus offering well principled and well understood algorithms for solving a variety of novel online problems.Read moreRead less
ARC Centre for Complex Systems. The Australian Centre for Complex Systems brings together leading researchers from several disciplines and institutions to conduct research on questions fundamental to understanding and managing complex systems. Its core research program, based on the theme of computation in and by networks of agents, has two interwoven strands. The science strand addresses questions about emergent properties, natural computation, and nonlinear dynamics. The engineering strand add ....ARC Centre for Complex Systems. The Australian Centre for Complex Systems brings together leading researchers from several disciplines and institutions to conduct research on questions fundamental to understanding and managing complex systems. Its core research program, based on the theme of computation in and by networks of agents, has two interwoven strands. The science strand addresses questions about emergent properties, natural computation, and nonlinear dynamics. The engineering strand addresses issues about methodology, modelling toolkits, and management and control. Practical applications are advanced via collaborative projects that address key issues in biology, environment, and socio-economics.Read moreRead less
The Physics of Network Computation. This project combines expertise in nonlinear soliton physics and computational sciences in order to provide new insights into the physics of network computation. Our proposal addresses the mathematics and computer modelling underlying nonconscious problem solving. We develop a new template concept, the meta-mode, which embodies the network structure of knowledge and the linking mechanisms, which underpin human creativity. We establish the optimal connectiv ....The Physics of Network Computation. This project combines expertise in nonlinear soliton physics and computational sciences in order to provide new insights into the physics of network computation. Our proposal addresses the mathematics and computer modelling underlying nonconscious problem solving. We develop a new template concept, the meta-mode, which embodies the network structure of knowledge and the linking mechanisms, which underpin human creativity. We establish the optimal connectivity distributions to preserve distinct pattern classes yet allow model radical shifts in paradigms, and develop algorithms for autonomous connectivity optimisation. We investigate nonlinear process such as solitons and random Boolean networks as realisations of these principles.Read moreRead less