人工智能的理解理论:可组合性、催化剂与学习
A theory of understanding for artificial intelligence: composability, catalysts, and learning
AI总结:
本研究提出基于可组合性的AI理解分析框架,引入催化剂概念分析提升输出的输入及主体结构,指出学习能力是将输入转化为内部催化剂的能力,语言模型等自催化模型为突破AI理解局限奠基。
摘要:
理解是人工智能(AI)领域中一个至关重要却又难以捉摸的概念。本研究提出了一个基于可组合性概念的理解分析框架。对于任何主体(例如人类或AI),我们建议从验证者的视角,以其将相关输入处理(组合)为令人满意的输出的能力,来表征其对某一对象的理解程度。这一具有高度普适性的框架可轻松应用于非人类主体,例如AI、非人类动物和机构。此外,我们提出了分析在组合过程中提升输出质量的输入的方法,我们将这类输入称为催化剂。我们展示了如何通过分析主体中充当催化剂的组成部分来揭示其结构,并提出主体的学习能力可被视为其将输入组合为自身内部催化剂的能力。最后,我们探讨了学习能力对于AI实现通用智能的重要性。我们的分析表明,能够生成可作为自身催化剂的输出的模型(例如语言模型),为潜在克服AI理解方面的现有局限性奠定了基础。
英文摘要:
Understanding is a crucial yet elusive concept in artificial intelligence (AI). This work proposes a framework for analyzing understanding based on the notion of composability. Given any subject (e.g., a person or an AI), we suggest characterizing its understanding of an object in terms of its ability to process (compose) relevant inputs into satisfactory outputs from the perspective of a verifier. This highly universal framework can readily apply to non-human subjects, such as AIs, non-human animals, and institutions. Further, we propose methods for analyzing the inputs that enhance output quality in compositions, which we call catalysts. We show how the structure of a subject can be revealed by analyzing its components that act as catalysts and argue that a subject's learning ability can be regarded as its ability to compose inputs into its inner catalysts. Finally we examine the importance of learning ability for AIs to attain general intelligence. Our analysis indicates that models capable of generating outputs that can function as their own catalysts, such as language models, establish a foundation for potentially overcoming existing limitations in AI understanding.
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。