Pattern analysis for accelerating scientific innovation

该项目旨在确定如何利用模式识别来加速和扩大支持科学创新的实验优化能力。这个新框架将颠覆目前的实验方法，使用数据驱动的模型来指导人类完成复杂的实验。该项目的预期成果包括通过解决基本问题和解释性问题，推进贝叶斯优化中模式识别的理论和实践，完全改变复杂的实验探索的方式。该项目将使澳大利亚成为第四次工业革命中以创新为主导的生产力的领导者，其中包括对使用模式识别在实验过程中导航复杂性的开创性研究。

This project aims to determine how pattern recognition can be harnessed to accelerate and expand the capability of experimental optimisation that underpins scientific innovation. Disrupting current experimental methods, this new framework will use data-driven models to guide humans through experimental complexity. The expected outcomes of the project include advancing the theory and practice of pattern recognition in Bayesian optimisation by solving both fundamental and translatory problems, totally transforming the way complex experimental explorations can be done. The project will establish Australia as a leader in innovation-led productivity in the 4th industrial revolution, which will include ground-breaking investigations into the use of pattern recognition to navigate complexity in the experimental process.