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
3D Image segmentation and shape characterisation driven by topological persistence. Tomographic imaging is emerging as a new tool to help tackle a remarkable array of scientific challenges. What distinguishes healthy bone from that of osteoporosis sufferers? How does groundwater contamination spread? Why is a macadamia nut so hard to crack? What causes the iridescence in a butterfly wing? These are just a few of the questions being answered at tomographic facilities in Australia alone. By co ....3D Image segmentation and shape characterisation driven by topological persistence. Tomographic imaging is emerging as a new tool to help tackle a remarkable array of scientific challenges. What distinguishes healthy bone from that of osteoporosis sufferers? How does groundwater contamination spread? Why is a macadamia nut so hard to crack? What causes the iridescence in a butterfly wing? These are just a few of the questions being answered at tomographic facilities in Australia alone. By combining sophisticated mathematics with cutting edge image-processing algorithms, this project will yield a new class of topology driven image analysis techniques that will improve the accuracy and reliability of predictions made from tomographic images.Read moreRead less
Automated Determination of the Pose of a Human from Visual Information - Markerless 3D Pose Recovery of Humans from Videos. The development of 3D human pose recovery has been sought by computer vision researchers for many years. Our results will, firstly, have benefit for Australia's standing in the international computer vision community. Over time, the research outcomes will be developed into a software product for rehabilitation analysis by recognizing discrepancies between the walking pat ....Automated Determination of the Pose of a Human from Visual Information - Markerless 3D Pose Recovery of Humans from Videos. The development of 3D human pose recovery has been sought by computer vision researchers for many years. Our results will, firstly, have benefit for Australia's standing in the international computer vision community. Over time, the research outcomes will be developed into a software product for rehabilitation analysis by recognizing discrepancies between the walking patterns of healthy individuals and those with abnormalities as a result of accidents or diseases. The Australian economy will benefit by the reduction in the lifetime cost of injuries. This software will also provide benefits to the movie animation, computer games industry, and the training of athletes.Read moreRead less
Bayesian inference for complex regression models using mixtures. The project will use mixtures to flexibly model complex regression functions and will develop Bayesian methods for carrying out statistical inference on these models. The models will deal with both Gaussian and non-Gaussian data. Multiple explanatory variables are dealt with by mixing simple additives to produce flexible high dimensional function estimates. Variable selection and model averaging will be used to identify important v ....Bayesian inference for complex regression models using mixtures. The project will use mixtures to flexibly model complex regression functions and will develop Bayesian methods for carrying out statistical inference on these models. The models will deal with both Gaussian and non-Gaussian data. Multiple explanatory variables are dealt with by mixing simple additives to produce flexible high dimensional function estimates. Variable selection and model averaging will be used to identify important variables and thus make the estimation more efficient. The methods will be extended to multivariate responses where account will taken be taken of the structure of the dependence between responses.Read moreRead less
The Time-Varying Eigenvalue Problem with Application to Signal Processing and Control. Linear models are ubiquitous in representing physical processes. Decomposing a linear model into its fundamental components is known as the eigenvalue problem. In applications as wide ranging as astronomy, aircraft control systems, Internet search engines and communication systems, it is necessary to perform this decomposition of a pertinent time varying linear model on the fly. This project aims to develop si ....The Time-Varying Eigenvalue Problem with Application to Signal Processing and Control. Linear models are ubiquitous in representing physical processes. Decomposing a linear model into its fundamental components is known as the eigenvalue problem. In applications as wide ranging as astronomy, aircraft control systems, Internet search engines and communication systems, it is necessary to perform this decomposition of a pertinent time varying linear model on the fly. This project aims to develop significantly faster and more accurate algorithms for this time varying eigenvalue problem than currently exist. Very modern techniques will be employed to achieve this aim, and the potential benefits to Australian hi-tech industries are great.
Read moreRead less
Special Research Initiatives - Grant ID: SR0354793
Funder
Australian Research Council
Funding Amount
$10,000.00
Summary
A Neural Network: Understanding Brain Function. This proposal focuses on the mechanisms that regulate brain function, particularly those underpinning the changes in circuitry (plasticity) caused by altered inputs. As such, its core goal is to create an interface between researchers in the neurosciences, computational modelling, robotics and cognitive sciences in order to facilitate optimum collaborative interactions, identify key research questions and promote training opportunities across a mul ....A Neural Network: Understanding Brain Function. This proposal focuses on the mechanisms that regulate brain function, particularly those underpinning the changes in circuitry (plasticity) caused by altered inputs. As such, its core goal is to create an interface between researchers in the neurosciences, computational modelling, robotics and cognitive sciences in order to facilitate optimum collaborative interactions, identify key research questions and promote training opportunities across a multidisciplinary spectrum. This will drive an integrated and accelerated program of discovery and technological development, enhancing Australia's leadership in this crucial field and helping to highlight new biotechnology opportunities and capture social and economic benefits for the nation. Read moreRead less
Integrating holistic processing and face-space approaches to the perception of facial identity. Recognising faces is a socially crucial task, and humans are remarkably good at it. Scientists investigating the 'software' our brains use to recognise faces have referred to two different theories -- one when explaining why we distinguish faces better than objects, and the other in explaining why we distinguish some people's faces more easily than others. The project aims to integrate these two theor ....Integrating holistic processing and face-space approaches to the perception of facial identity. Recognising faces is a socially crucial task, and humans are remarkably good at it. Scientists investigating the 'software' our brains use to recognise faces have referred to two different theories -- one when explaining why we distinguish faces better than objects, and the other in explaining why we distinguish some people's faces more easily than others. The project aims to integrate these two theories. This has two potential long-term benefits: it will give a stronger basis for understanding what goes wrong in people where face recognition does not develop normally; and, the improved knowledge from a biological system may also lead to improved computer face recognition algorithms (eg. for airport security).Read moreRead less
Neurobiological computation using self organization. Despite their phenomenal power and speed there are many simple things that computers still cannot do, that humans, and indeed many animals, are able to perform effortlessly. The research outlined in this proposal aims to develop new, biologically inspired, computational approaches that attempt to bridge this gap. This research will help place Australia, despite its relatively small size, as a leading research community in the development of ....Neurobiological computation using self organization. Despite their phenomenal power and speed there are many simple things that computers still cannot do, that humans, and indeed many animals, are able to perform effortlessly. The research outlined in this proposal aims to develop new, biologically inspired, computational approaches that attempt to bridge this gap. This research will help place Australia, despite its relatively small size, as a leading research community in the development of the next wave of computing devices. The development of new and "more natural" approaches to computing will deliver large dividends to a range of social, economic and environmental problems.Read moreRead less
Asynchronous Continuous Time Conditioning. Methodology for reasoning about Asynchronous Temporal Conditional Events (ATCE) obtains, complete with logical calculus for causal relations, reasoning about continuous time belief change, and markov chain algorithms calculating joint distributions of ATCE's.
Current techniques, including bayesian nets, are oblivious to temporal aspects; within our model they can be enhanced to recognize dynamic time changes. Ours is the first such unified model and ....Asynchronous Continuous Time Conditioning. Methodology for reasoning about Asynchronous Temporal Conditional Events (ATCE) obtains, complete with logical calculus for causal relations, reasoning about continuous time belief change, and markov chain algorithms calculating joint distributions of ATCE's.
Current techniques, including bayesian nets, are oblivious to temporal aspects; within our model they can be enhanced to recognize dynamic time changes. Ours is the first such unified model and first to link conditional objects with continuous time constraints.
Need for structures we propose arises in diagnostic reasoning, bayesian learning, temporal databases, and time-dependent data mining. Several commercial products (like Microsoft Office Assistant)could apply them forthwith.Read moreRead less
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