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
Discovery Early Career Researcher Award - Grant ID: DE240100144
Funder
Australian Research Council
Funding Amount
$444,447.00
Summary
Universal Model Selection Criteria for Scientific Machine Learning. This project aims to develop provably reliable universal model selection criteria to facilitate trustworthy scientific machine learning. Combining stochastic methods with an innovative geometric approach to basic statistical principles, this project expects to characterise, combine, and refine the most successful heuristics for designing and training huge models, such as deep neural networks, into a cohesive theoretical framewor ....Universal Model Selection Criteria for Scientific Machine Learning. This project aims to develop provably reliable universal model selection criteria to facilitate trustworthy scientific machine learning. Combining stochastic methods with an innovative geometric approach to basic statistical principles, this project expects to characterise, combine, and refine the most successful heuristics for designing and training huge models, such as deep neural networks, into a cohesive theoretical framework. The expected outcomes include a general toolkit for assisting neural network design at the forefront of scientific applications. This should significantly improve the quality of scientific predictions by facilitating confident adoption of deep learning methods into the pantheon of trustworthy modeling techniques. Read moreRead less
Accelerated Finite-time Learning and Control in Cyber-Physical Systems. Efficient learning and control in cyber-physical systems such as smart grids and robotic systems are very important for achieving economic and social benefits. This project aims to establish a breakthrough accelerated finite-time dynamics theory and technology to assist in delivering efficient learning and control. Expected outcomes include new distributed accelerated finite-time dynamics based learning and control algorithm ....Accelerated Finite-time Learning and Control in Cyber-Physical Systems. Efficient learning and control in cyber-physical systems such as smart grids and robotic systems are very important for achieving economic and social benefits. This project aims to establish a breakthrough accelerated finite-time dynamics theory and technology to assist in delivering efficient learning and control. Expected outcomes include new distributed accelerated finite-time dynamics based learning and control algorithms and tools for optimal operations in cyber-physical systems. This should provide significant benefits including a practical technology for industry applications in smart grids and robotic systems, and training of the next generation engineers in this technology for Australia.Read moreRead less
Using cognitive models to understand memorability of real world images. This proposal aims to understand and make predictions about which real world images -- specifically living things, objects, and human faces -- that people will remember remember via an integration of cognitive models of memory and machine learning techniques. Computer vision models and similarity scaling techniques will be used to produce psychological representations of the images. These representations will then be integra ....Using cognitive models to understand memorability of real world images. This proposal aims to understand and make predictions about which real world images -- specifically living things, objects, and human faces -- that people will remember remember via an integration of cognitive models of memory and machine learning techniques. Computer vision models and similarity scaling techniques will be used to produce psychological representations of the images. These representations will then be integrated with cognitive models of memory, which predict that images are more likely to be recognized if they are similar to each of the representations in memory. Large scale memory and similarity rating datasets will be used to develop and test the model.Read moreRead less
Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models ....Small Scalable Natural Language Models using Explicit Memory. Deep neural networks have had spectacular success in natural language processing, seeing wide-spread deployment as part of automatic assistant devices in homes and cars, and across many valuable industries including finance, medicine and law. Fueling this success is the use of ever larger models, with exponentially increasing training resources, accompanying hardware and energy demands. This project aims to develop more compact models, based on the incorporation of an explicit searchable memory, which will dramatically reduce model size, hardware requirements and energy usage. This will make modern natural language processing more accessible, while also providing greater flexibility, allowing for more adaptable and portable technologies.Read moreRead less