Interpretable Behaviour Analysis with External Structured Knowledge

使用外部结构化知识进行可解释的行为分析

• 批准号: DP220100769
• 负责人: Prof Michael Blumenstein
• 金额: $ 24.82万
• 依托单位: University of Technology Sydney
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2022
• 资助国家: 澳大利亚
• 起止时间: 2022-01-01 至 2024-12-31
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP220100769
• 关键词: Interpretable; Behaviour; Analysis; External; Structured

This project aims to develop novel interpretable neural models for predictive analytics tasks on human behaviour, operating on sequence behaviour data associated with external supportive structured knowledge. It is expected to present theoretical foundations for robust representation learning on heterogeneous behaviour data and interpretable machine reasoning models, which can support a broad scope of intelligent systems. Expected outcomes will be a next-generation interpretable behaviour analysis system with versatile abilities to reason over various data structures and provide a high-level interpretability about its reasoning procedure. The benefits will span the research and industry sectors, e.g., retail, healthcare, service provider.

该项目旨在开发新颖的可解释神经模型，用于人类行为的预测分析任务，对与外部支持性结构化知识相关的序列行为数据进行操作。预计将为异构行为数据和可解释的机器推理模型的鲁棒表示学习提供理论基础，从而支持广泛的智能系统。预期的结果将是下一代可解释的行为分析系统，具有对各种数据结构进行推理的多功能能力，并为其推理过程提供高级可解释性。这些好处将涵盖研究和工业部门，例如零售、医疗保健、服务提供商。