In-vivo functional imaging of cone photoreceptors and ganglion cell axons. Can we project a movie on a human retina, and measure the response of photoreceptor cells and connected nerve tissue? This project aims to investigate a new method for visualization of the quickest responses in human cone photoreceptors and nerve cells after a visible stimulus. Expected outcomes of this project include a better understanding of the origins of responses to a stimulus and how cells in the retina communicate ....In-vivo functional imaging of cone photoreceptors and ganglion cell axons. Can we project a movie on a human retina, and measure the response of photoreceptor cells and connected nerve tissue? This project aims to investigate a new method for visualization of the quickest responses in human cone photoreceptors and nerve cells after a visible stimulus. Expected outcomes of this project include a better understanding of the origins of responses to a stimulus and how cells in the retina communicate. The scientific results will be helpful in a better understanding of the development of vision in the infant eye, to study peripheral vision in elite athletes and to quantify performance of virtual reality equipment for the military. The IP on the technology can be licensed or used for start-up company.Read moreRead less
Deep Learning that Scales. Deep learning has dramatically improved the accuracy of a breathtaking variety of tasks in AI such as image understanding and natural language processing. This project addresses fundamental bottlenecks when attempting to develop deep learning applications at scale. First, this project proposes efficient neural architecture search that is orders of magnitude faster than previously reported, abstracting away the most complex part of deep learning. Second, we will desig ....Deep Learning that Scales. Deep learning has dramatically improved the accuracy of a breathtaking variety of tasks in AI such as image understanding and natural language processing. This project addresses fundamental bottlenecks when attempting to develop deep learning applications at scale. First, this project proposes efficient neural architecture search that is orders of magnitude faster than previously reported, abstracting away the most complex part of deep learning. Second, we will design very efficient binary networks, enabling large-scale deployment of deep learning to mobile devices. Thus this project will overcome two primary limitations of deep learning generally, however, and will greatly increase its already impressive domain of practical application.Read moreRead less
Ultra-low fouling active surfaces. This project aims to develop chemistries and fabrication approaches through innovative materials evaluation to develop ultra-low fouling active electrode surfaces. Development of ultra-low fouling surfaces will have significant impact in a range of applications where system or device failure is attributed to fouling. The growing field of bionics, where implantable electronic devices interface directly with the nervous system, is one such device. The expected ou ....Ultra-low fouling active surfaces. This project aims to develop chemistries and fabrication approaches through innovative materials evaluation to develop ultra-low fouling active electrode surfaces. Development of ultra-low fouling surfaces will have significant impact in a range of applications where system or device failure is attributed to fouling. The growing field of bionics, where implantable electronic devices interface directly with the nervous system, is one such device. The expected outcomes will be an understanding of the material requirements that lead to the elimination of protein and cell accumulation at surfaces that degrades the performance and lifetime of these implants. The findings will benefit any application where fouling is a problem.Read moreRead less
Biological determinants of the safety and stability of neuroprosthetic stimulation electrodes. Performance of cochlear implants and the quality of sound perceived by patients is strongly related to electrode impedance. Electrode impedance fluctuates relative to the implant electrical activity, but the mechanisms which cause this are not clear. This project aims to investigate the role of protein adsorption in electrode performance, including impedance and material dissolution. To enable these in ....Biological determinants of the safety and stability of neuroprosthetic stimulation electrodes. Performance of cochlear implants and the quality of sound perceived by patients is strongly related to electrode impedance. Electrode impedance fluctuates relative to the implant electrical activity, but the mechanisms which cause this are not clear. This project aims to investigate the role of protein adsorption in electrode performance, including impedance and material dissolution. To enable these investigations a new biomimetic analogue of the perilymph (cochlea fluid) is intended to be developed. Additionally, the project aims to investigate two strategies to minimise impedance changes: small pulse electrode cleaning and antifouling coatings. Understanding and control of factors influencing electrode stability aim to facilitate next-generation implant designs.Read moreRead less
Adapting Deep Learning for Real-world Medical Image Datasets. The project aims to investigate new deep learning modelling approaches to leverage real-world large-scale image data sets that contain noisy and incomplete labels and imbalanced class prevalence – to enable the use of these data sets for modelling deep learning classifiers. Expected outcomes include an innovative method for modelling deep learning classifiers. The research will involve new inter-disciplinary and international collabor ....Adapting Deep Learning for Real-world Medical Image Datasets. The project aims to investigate new deep learning modelling approaches to leverage real-world large-scale image data sets that contain noisy and incomplete labels and imbalanced class prevalence – to enable the use of these data sets for modelling deep learning classifiers. Expected outcomes include an innovative method for modelling deep learning classifiers. The research will involve new inter-disciplinary and international collaborations with machine learning and medical image analysis research institutions. This should provide significant benefits, such as better understanding of deep learning theory, new deep learning applications that can use previously unexplored data sets, and training for the future Australian workforce.Read moreRead less
The role of strong duality in computer vision. This project aims to undertake research in the fields of computer vision and optimization that will have a significant impact on the design of numerical algorithms for solving a wide range of problems in Computer Vision, Virtual Reality and Robotic Navigation. This project will advance understanding of a broad class of problems related to how computers interpret images. An expected outcome is the generation of novel mathematical theory and numerical ....The role of strong duality in computer vision. This project aims to undertake research in the fields of computer vision and optimization that will have a significant impact on the design of numerical algorithms for solving a wide range of problems in Computer Vision, Virtual Reality and Robotic Navigation. This project will advance understanding of a broad class of problems related to how computers interpret images. An expected outcome is the generation of novel mathematical theory and numerical algorithms capable of fundamentally changing the way problems relevant to a wide range of vision-related applications are solved. This should offer Australia a strong competitive advantage as a leader in scientific innovation in the areas of Computer Vision, Virtual Reality and Robotics and Autonomous Systems.Read moreRead less
Automated analysis of multi-modal medical data using deep belief networks. This project will develop an improved breast cancer computer-aided diagnosis (CAD) system that incorporates mammography, ultrasound and magnetic resonance imaging. This system will be based on recently developed deep learning techniques, which have the capacity to process multi-modal data in a unified and optimal manner. The advantage of this technique is that it is able to automatically learn both the relevant features t ....Automated analysis of multi-modal medical data using deep belief networks. This project will develop an improved breast cancer computer-aided diagnosis (CAD) system that incorporates mammography, ultrasound and magnetic resonance imaging. This system will be based on recently developed deep learning techniques, which have the capacity to process multi-modal data in a unified and optimal manner. The advantage of this technique is that it is able to automatically learn both the relevant features to analyse in each modality and the hidden relationships between them. The use of deep belief networks has produced promising results in several fields, such as speech recognition, and so this project believes that our approach has the potential to improve both the sensitivity and specificity of breast cancer detection.Read moreRead less
Targeting electrical stimulation of neural tissue. This project aims to develop a platform of mathematical methods for targeting electrical stimulation of neural tissue. The proposed methods work by selecting the amplitude and polarity of each stimulating electrode in an array based on a desired pattern of neural activation. The algorithms are particularly applicable to high-density electrode arrays. The project will work with an Australian industry leader to provide significant benefits to Aust ....Targeting electrical stimulation of neural tissue. This project aims to develop a platform of mathematical methods for targeting electrical stimulation of neural tissue. The proposed methods work by selecting the amplitude and polarity of each stimulating electrode in an array based on a desired pattern of neural activation. The algorithms are particularly applicable to high-density electrode arrays. The project will work with an Australian industry leader to provide significant benefits to Australia’s high-tech sector through increased knowledge and capacity.Read moreRead less
Feedthrough technologies for polymeric encapsulated active implants. The project will address the scientific challenges of signal transfer between tissue and novel active implantable medical devices, with major implications for cochlear implant manufacture. This will lead to improvements in the quality of life of the hearing-impaired, and will make an important contribution to the development of other sensory implants.
Development of a three dimensional audio-visual next generation speech recognition system. To overcome the disadvantages of current Audio-Visual Speech Recognition Systems, we propose a set of robust algorithms in three dimensional computer vision and speech processing. The proposed system will have far-reaching implications in various areas, for example, human-machine interaction for speech recognition in automated dialog systems and voice-to-text conversions.