arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.13512cs.AIcs.CVcs.RO
收藏

投影:人工智能中的类人推理机制

Projection: A Mechanism for Human-like Reasoning in Artificial Intelligence

University of Surrey(萨里大学)

Frank Guerin

摘要:

人工智能系统还不能与人类的能力相匹配,将知识应用于与它们被编程或训练的情况不同的情况。在视觉对象识别中,利用自上而下的信息(来自模型)的推理方法已被证明对于在困难条件下识别实体是有效的。在这里,这种类型的推理,称为“投影”,被证明是解决将知识应用于各种或具有挑战性的情况的问题的关键机制,涉及一系列人工智能领域,如视觉,机器人或语言。最后讨论了投影与解决常识问题的相关性。

英文摘要:

Artificial Intelligence systems cannot yet match human abilities to apply knowledge to situations that vary from what they have been programmed for, or trained for. In visual object recognition methods of inference exploiting top-down information (from a model) have been shown to be effective for recognising entities in difficult conditions. Here this type of inference, called `projection', is shown to be a key mechanism to solve the problem of applying knowledge to varied or challenging situations, across a range of AI domains, such as vision, robotics, or language. Finally the relevance of projection to tackling the commonsense knowledge problem is discussed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑