让AI像人一样在新环境中理解事物，通过记忆重组构建新意义
Sensemaking in Novel Environments: How Human Cognition Can Inform Artificial Agents
- 用符号关系框架整合多源知识，实现跨情境理解
- 通过共享属性重组记忆，生成新概念符号应对未知场景
- 适合研究认知智能与通用AI的学者参考
人类核心认知能力之一是理解世界中的物体、事件和情境。本文提出一种方法，使人工智能代理具备在陌生环境中进行意义建构的能力。核心思想包括：(1) 构建统一的意义建构概念框架，包含框架内及跨框架的符号关系；(2) 通过共享属性，使多种内容可寻址、分布式知识结构相互作用，其综合响应形成合成符号，用于在陌生环境中表征特定结果，实现意义建构。研究表明，记忆中的属性可被重新组合，以生成新符号，从而在未见过的环境中实现意义理解。
原文摘要 · Abstract (English)
One of the most vital cognitive skills to possess is the ability to make sense of objects, events, and situations in the world. In the current paper, we offer an approach for creating artificially intelligent agents with the capacity for sensemaking in novel environments. Objectives: to present several key ideas: (1) a novel unified conceptual framework for sensemaking (which includes the existence of sign relations embedded within and across frames); (2) interaction among various content-addressable, distributed-knowledge structures via shared attributes (whose net response would represent a synthesized object, event, or situation serving as a sign for sensemaking in a novel environment). Findings: we suggest that attributes across memories can be shared and recombined in novel ways to create synthesized signs, which can denote certain outcomes in novel environments (i.e., sensemaking).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。