Discovery Early Career Researcher Award - Grant ID: DE200101253
Funder
Australian Research Council
Funding Amount
$349,586.00
Summary
Making Machine Learning Fair(er). This project aims to develop and implement statistical methods to fight against algorithm bias. In doing so, this project expects to generate new knowledge in the mathematical sciences by employing innovative and interdisciplinary approaches to the development of fairness constraints on machine learning algorithms. Fairness will be seen through the lens of invariance, allowing the developed conceptual framework to find broad applications. Expected outcomes of t ....Making Machine Learning Fair(er). This project aims to develop and implement statistical methods to fight against algorithm bias. In doing so, this project expects to generate new knowledge in the mathematical sciences by employing innovative and interdisciplinary approaches to the development of fairness constraints on machine learning algorithms. Fairness will be seen through the lens of invariance, allowing the developed conceptual framework to find broad applications. Expected outcomes of this project include improved techniques for imposing invariance on deep learning algorithms. This should provide significant benefits to the general public by contributing to the advancement of socially responsible and conscientious machine learning.Read moreRead less
Mathematical modelling of information flow in social networks. This proposal aims to develop new mathematical and statistical methods to understand information flow in social networks. By using novel information theoretic techniques, it will create new methods to characterise social information flow in social networks. These tools will allow derivation of fundamental limits of predictability for AI methods applied to digital data. New mathematics of information flow will produce insights into so ....Mathematical modelling of information flow in social networks. This proposal aims to develop new mathematical and statistical methods to understand information flow in social networks. By using novel information theoretic techniques, it will create new methods to characterise social information flow in social networks. These tools will allow derivation of fundamental limits of predictability for AI methods applied to digital data. New mathematics of information flow will produce insights into social influence in online social networks. Benefits include: better understanding of how echo chambers may form in social networks, predictive models for how misinformation can spread online such as during an emergency, and a framework for intercomparison of AI methods applied to digital data on individuals. Read moreRead less
Optimising progress towards elimination of malaria. The project aims to advance mathematical knowledge by developing novel tools appropriate for modelling disease elimination. We will apply these new mathematical tools to the significant problem of malaria elimination in Vietnam. The expected outcomes are new tools for modelling disease elimination on a fine spatial resolution with heterogeneities in individual patient characteristics, calibrating models to household level data on disease transm ....Optimising progress towards elimination of malaria. The project aims to advance mathematical knowledge by developing novel tools appropriate for modelling disease elimination. We will apply these new mathematical tools to the significant problem of malaria elimination in Vietnam. The expected outcomes are new tools for modelling disease elimination on a fine spatial resolution with heterogeneities in individual patient characteristics, calibrating models to household level data on disease transmission and designing intervention strategies for maximum effect on disease transmission. The innovative combination of modelling, inference and optimisation ensures that the mathematical methods developed will be broadly applicable to modelling elimination strategies for other infectious diseases.
Read moreRead less