Uncertainty, Risk and Related Concepts in Machine Learning

机器学习中的不确定性、风险和相关概念

• 批准号: DP150104595
• 负责人: Prof Robert Williamson
• 金额: $ 8.54万
• 依托单位: The Australian National University
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2015
• 资助国家: 澳大利亚
• 起止时间: 2015-06-30 至 2020-06-29
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP150104595
• 关键词: Uncertainty; Risk; Related; Concepts; Machine

Machine learning is the science of making sense of data. It does not and cannot remove all risk and uncertainty. This project proposes to study the foundations of how machine learning uses, represents and communicates risk and uncertainty. It aims to do so by finding new theoretical connections between diverse notions that have arisen in allied disciplines. These include risk, uncertainty, scoring rules and loss functions, divergences, statistics and different ways of aggregating information. By building a more complete theoretical map it is expected that new machine learning methods will be developed, but more importantly that machine learning will be able to be better integrated into larger socio-technical systems.

机器学习是理解数据的科学。它不会也不可能消除所有风险和不确定性。该项目旨在研究机器学习如何使用，表示和传达风险和不确定性的基础。它旨在通过在相关学科中出现的不同概念之间找到新的理论联系来做到这一点。这些因素包括风险、不确定性、评分规则和损失函数、分歧、统计和不同的信息汇总方式。通过构建更完整的理论地图，预计将开发新的机器学习方法，但更重要的是，机器学习将能够更好地融入更大的社会技术系统。