Probabilistic Networks for Automated Reasoning

用于自动推理的概率网络

• 批准号: 0535223
• 负责人: Judea Pearl
• 金额: --
• 依托单位: University of California-Los Angeles
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2005
• 资助国家: 美国
• 起止时间: 2005-11-01 至 2008-10-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0535223&HistoricalAwards=false
• 关键词: Probabilistic; Networks; Automated; Reasoning

The ultimate aim of this investigation is to develop computer systems capable of operating autonomously in dynamic and uncertain environments. Specifically, the investigation comprises theoretical and experimental studies in the following areas: (1) Information fusion, situation assessment, diagnosis, and planning under uncertainty using causal and counterfactual relationships; (2) Automatic generation of natural language explanations of actions, recommendations, and unexpected eventualities; and (3) Learning causal structures from data to facilitate predictions and decisions in data-intensive applications. Priority will be given to new methods of generation explanatory sentences and to structural learning tasks in molecular biology. The theoretical part of the research is fundamental to our understanding the structure of human knowledge and scientific inquiry, and could have far-reaching broader impact in the fields of epidemiology, social science, economics, medicine and biology, where causal knowledge plays a major role.

本研究的最终目的是开发能够在动态和不确定环境中自主运行的计算机系统。具体而言，调查包括以下领域的理论和实验研究：（1）信息融合，情况评估，诊断和规划下的不确定性，使用因果关系和反事实关系：（2）自动生成的自然语言解释的行动，建议，和意外事件;以及（3）从数据中学习因果结构，以促进数据密集型应用中的预测和决策。优先考虑的是生成解释性句子的新方法和分子生物学中的结构学习任务。研究的理论部分对于我们理解人类知识和科学探究的结构至关重要，并可能在流行病学，社会科学，经济学，医学和生物学领域产生深远的广泛影响，其中因果知识发挥着重要作用。