Evaluating models of category learning that use general feature-based representations. Three competing models of human category learning will be evaluated by comparing their behaviour to human performance on an experimental task where each model makes qualitatively different predictions. A series of theoretical and algorithmic advances will be undertaken to ensure each of the category learning models uses the same feature-based representation. Because the three models propose very different lear ....Evaluating models of category learning that use general feature-based representations. Three competing models of human category learning will be evaluated by comparing their behaviour to human performance on an experimental task where each model makes qualitatively different predictions. A series of theoretical and algorithmic advances will be undertaken to ensure each of the category learning models uses the same feature-based representation. Because the three models propose very different learning processes, their comparison will give insight into the basic cognitive process of categorisation. The algorithms for generating feature representations and modelling human category learning will also have potential for application in data visualisation and information handling systems.Read moreRead less
Hierarchical Bayesian Models for Human Conceptual Learning. This project seeks to understand the nature of human conceptual learning. With the shift to an information-based economy, it becomes important to understand what assumptions a real-world learning system should make. Even given the impressive growth of machine learning and artificial intelligence, the human mind remains the most successful example of such a system. In this light, the scientific study of human conceptual structure present ....Hierarchical Bayesian Models for Human Conceptual Learning. This project seeks to understand the nature of human conceptual learning. With the shift to an information-based economy, it becomes important to understand what assumptions a real-world learning system should make. Even given the impressive growth of machine learning and artificial intelligence, the human mind remains the most successful example of such a system. In this light, the scientific study of human conceptual structure presents the opportunity to discover how an intelligent thinking system should operate. In addition, many important problems facing an information economy involve being able to understand how people behave. An understanding of the concepts people use is central to this endeavour.Read moreRead less
Learning to Reason in Reinforcement Learning. Deep Reinforcement Learning (RL) uses deep neural networks to represent and learn optimal decision-making policies for intelligent agents in complex environments. However, most RL approaches require millions of episodes to converge to good policies, making it difficult for RL to be applied in real-world scenarios taking significant resources. This project aims to equip RL with capabilities such as counterfactual reasoning and outcome anticipation to ....Learning to Reason in Reinforcement Learning. Deep Reinforcement Learning (RL) uses deep neural networks to represent and learn optimal decision-making policies for intelligent agents in complex environments. However, most RL approaches require millions of episodes to converge to good policies, making it difficult for RL to be applied in real-world scenarios taking significant resources. This project aims to equip RL with capabilities such as counterfactual reasoning and outcome anticipation to significantly reduce the number of interactions required, improve generalisation, and provide the agent with the capability to consider the cause-effects. These improvements would narrow the gap between AI and human capabilities and broaden the adoption of RL in real-world applications.Read moreRead less
How are beliefs altered by data? Robust Bayesian models for human inductive learning. This project applies state of the art mathematical models to study how people think and reason, and how we can make good guesses about the future. The goal is to understand how the human mind can operate so effectively in real environments, when even the most powerful computers struggle to handle the complexities of everyday learning problems.
Making Meta-learning Generalised . This project aims to develop novel machine learning techniques, termed generalised meta-learning, to make machines better utilise past experience to solve new tasks with few data. It expects to reduce the undesirable dependence of current machine learning on labelled data and significantly expand its application scope. Expected outcomes of the project consist of new theoretical results on meta-learning and a set of innovative algorithms that can support the bui ....Making Meta-learning Generalised . This project aims to develop novel machine learning techniques, termed generalised meta-learning, to make machines better utilise past experience to solve new tasks with few data. It expects to reduce the undesirable dependence of current machine learning on labelled data and significantly expand its application scope. Expected outcomes of the project consist of new theoretical results on meta-learning and a set of innovative algorithms that can support the building of next generation of computer vision systems to work in open and dynamic environments. This should be able to produce solid benefits to the science, society, and economy of Australian via the application of these advanced intelligent systems.Read moreRead less
Uncovering the processes underlying human reasoning: A state-trace approach. This project aims to answer the most important unresolved question in the psychology of reasoning; how many distinct cognitive processes underlie human reasoning? To answer this question, this project aims to conduct an extensive experimental investigation of the factors that selectively impact inductive and deductive inferences and the application of high-dimensional state-trace analysis; a powerful new method for diag ....Uncovering the processes underlying human reasoning: A state-trace approach. This project aims to answer the most important unresolved question in the psychology of reasoning; how many distinct cognitive processes underlie human reasoning? To answer this question, this project aims to conduct an extensive experimental investigation of the factors that selectively impact inductive and deductive inferences and the application of high-dimensional state-trace analysis; a powerful new method for diagnosing underlying processes from behavioural data. The project is expected also to develop a new computational model that accounts for both inductive and deductive forms of reasoning.Read moreRead less
Build competency aware and assuring machine learning systems. Recent development in machine learning (ML) has seen ML models with extremely high prediction accuracy. However, to support human-machine partnership in decision-making in complex environments, beyond accuracy, it is essential for ML systems to be competency aware and reliable, and at the same time be exploratory. This project aims to develop novel techniques to equip a ML system with the ability to identify own competency, to justify ....Build competency aware and assuring machine learning systems. Recent development in machine learning (ML) has seen ML models with extremely high prediction accuracy. However, to support human-machine partnership in decision-making in complex environments, beyond accuracy, it is essential for ML systems to be competency aware and reliable, and at the same time be exploratory. This project aims to develop novel techniques to equip a ML system with the ability to identify own competency, to justify its competency and decisions, to explore unknown situations and fully utilise existing expertise to deal with unknowns. The expected outcomes of the project will enable ML systems to become truely intelligent and reliable machine partners for human decision makers in a wide range of applications.Read moreRead less
Where do inductive biases come from? A Bayesian investigation. This project aims to investigate the origin of our thinking and learning biases using state-of-the-art mathematical models and sophisticated experimental designs. Expected outcomes include bridging the gap between human and machine learning by pairing mathematical modelling with experimental work, forming a necessary step toward the development of machine systems that can reason like people do. This will provide significant benefits ....Where do inductive biases come from? A Bayesian investigation. This project aims to investigate the origin of our thinking and learning biases using state-of-the-art mathematical models and sophisticated experimental designs. Expected outcomes include bridging the gap between human and machine learning by pairing mathematical modelling with experimental work, forming a necessary step toward the development of machine systems that can reason like people do. This will provide significant benefits such as understanding how people operate so effectively in real environments, when even the most powerful computers struggle to handle the complexities of everyday learning problems.Read moreRead less
Learning from others: Inductive reasoning based on human-generated data. Most of the data we see every day, from politics to gossip, comes from other people. Making inferences about such data is difficult because the people who provided it may have biases or limitations in their knowledge that we do not know about and must figure out. This project uses a series of experiments tied to normative computational models of social reasoning to explore how people solve this problem. This work has the po ....Learning from others: Inductive reasoning based on human-generated data. Most of the data we see every day, from politics to gossip, comes from other people. Making inferences about such data is difficult because the people who provided it may have biases or limitations in their knowledge that we do not know about and must figure out. This project uses a series of experiments tied to normative computational models of social reasoning to explore how people solve this problem. This work has the potential to make a major impact in understanding how information is understood and shared, especially when it is about topics that people lack firsthand knowledge about, like climate change. The computational models also have applications to the development of expert systems upon which our information economy relies.Read moreRead less
Advancing the visualisation and quantification of nephrons with MRI. . This project aims to characterise key components of nephrons, the glomeruli and tubules, using magnetic resonance imaging without contrast agents, in combination with Deep Learning and super-resolution techniques. Nephrons, the basic functional unit of the kidney, are critical to the maintenance of the body’s homeostasis. Their number and architecture are critical determinants of kidney function. The expected outcomes are inn ....Advancing the visualisation and quantification of nephrons with MRI. . This project aims to characterise key components of nephrons, the glomeruli and tubules, using magnetic resonance imaging without contrast agents, in combination with Deep Learning and super-resolution techniques. Nephrons, the basic functional unit of the kidney, are critical to the maintenance of the body’s homeostasis. Their number and architecture are critical determinants of kidney function. The expected outcomes are innovative semi-automated nephron visualisation and quantitation tools that enable efficient renal phenotyping. Techniques tailored to widely accessible preclinical research scanners are expected to accelerate research into genetic and environmental factors affecting kidney microstructure in embryonic and post-natal life.Read moreRead less