Universal Model Selection Criteria for Scientific Machine Learning

科学机器学习的通用模型选择标准

• 批准号: DE240100144
• 负责人: Dr Liam Hodgkinson
• 金额: $ 30.77万
• 依托单位: The University of Melbourne
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Early Career Researcher Award
• 财政年份: 2024
• 资助国家: 澳大利亚
• 起止时间: 2024-01-01 至 2026-12-31
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DE240100144
• 关键词: Universal; Model; Selection; Criteria; Scientific

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.

该项目旨在开发可证明可靠的通用模型选择标准，以促进可信的科学机器学习。该项目将随机方法与基本统计原理的创新几何方法相结合，希望将最成功的设计和训练大型模型（如深度神经网络）的方法进行整合、联合收割机和改进，形成一个有凝聚力的理论框架。预期成果包括一个通用工具包，用于在科学应用的最前沿协助神经网络设计。通过促进深度学习方法自信地应用到值得信赖的建模技术中，这应该会显着提高科学预测的质量。