RUI: Efficient Reasoning with Massive Parallelism and Hybrid Techniques
RUI: Efficient Reasoning with Massive Parallelism and Hybrid Techniques
批准号:
9204655
负责人:
James Geller
金额:
$2.95万
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
1992
资助国家:
美国
项目状态:
已结题
起止时间:
1992-05-15 至 1993-10-31
中文摘要
这个项目关注的是为通用人工智能构建一个快速的、理论上有充分依据的推理器——一个大规模并行传递树推理器。人工智能推理算法通常很棘手,也就是说,它们对于任何实际问题的规模都太慢,无法发挥真正的价值。克服这些问题的一种广泛使用的方法是创建特殊目的推理器。这样的推理器只能解决非常有限的一组问题,而且在架构上太受限制了。本研究旨在设计一种比现有的专用推理器更通用、比现有的通用推理器更快的推理器。这个推理器将有一个与通用推理器定义良好的接口。
英文摘要
This project is concerned with building a fast and theoretically well founded reasoner - a massively parallel transitivity-tree reasoner - for general AI. AI reasoning algorithms are often intractable, that is they are too slow for any practical problem sizes to be of real value. A widely used approach to overcome these problems has been to create special purpose reasoners. Such reasoners solve only a very limited set of problems, and are too restricted in architecture. This research is aimed at designing a reasoner that is more general than current special purpose reasoners and faster than existing general reasoners. This reasoner will have a well defined interface to a general purpose reasoner.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Applying Student Knowledge for Success in Cybersecurity and Data Science
-
批准号:2129807
-
项目类别:Standard Grant
-
资助金额:$138.48万
-
财政年份:2021
-
负责人:James Geller
-
依托单位:
海外基金