Physics-informed and physics-constrained machine learning for next generation imaging

用于下一代成像的物理知情和物理约束的机器学习

• 批准号: 2898384
• 金额: --
• 依托单位: University of Glasgow
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2898384
• 关键词: Physics; informed; physics; constrained; machine; Physics; informed; physics; constrained; machine

Physics-informed and physics-constrained machine learning for next generation imaging.A team of researchers from the University of Glasgow and the "big image data" company, Dotphoton. The student will be part of a multidisciplinary team of physicists and working on novel imaging techniques, of computer scientists working on novel machine learning approaches that encode the physics of the imaging problem and bio-engineers working with cutting edge microscopy techniques. The ambition is to develop new-generation, physics-constrained AI that can image better, faster and more intelligently that current systems. By embedding physical constraints in to the design of the AI, you will develop better microscopes and biological imaging techniques that will be tested on new-generation fluorescence microscopes and healthcare monitoring devices. The research will be carried out at the Advanced Research Centre (ARC) in Glasgow, where you will work with a team of physicists, computing scientists, engineers and biologists. The project will be in close collaboration with Dotphoton (Switzerland) and will ideally involve also in-person visits to the company premises to work with their team of data scientists.

下一代成像的物理信息和物理受限的机器学习。来自格拉斯哥大学的研究人员和“大图像数据”公司Dotphoton。该学生将成为一个跨学科的物理学家团队的一部分，并从事新型成像技术，计算机科学家从事新颖机器学习方法的计算机科学家，该方法编码了成像问题的物理和生物工程师的物理学方法，并使用尖端显微镜技术工作。野心是开发新代，物理受限的AI，可以更好，更快，更明智地对当前系统进行映像。通过将物理约束嵌入AI的设计中，您将开发出更好的显微镜和生物成像技术，这些技术将在新的荧光显微镜和医疗保健监测设备上进行测试。该研究将在格拉斯哥的高级研究中心（ARC）进行，您将与一组物理学家，计算科学家，工程师和生物学家一起工作。该项目将与Dotphoton（瑞士）密切合作，理想情况下也将涉及到公司场所的亲自访问，与他们的数据科学家团队合作。