我们为何关注理解：通过预测压缩获得能力
Why We Care About Understanding: Competence through Predictive Compression
查看机构详情
- University of Bern（伯尔尼大学）
- École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
- Idiap Research Institute（Idiap研究所）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文通过三个关联论点弥合了信息论等领域将理解等同于压缩的观点与哲学家对理解的定义，解释了人类理解的压缩形式及AI系统的不可解释性。
中文摘要 AI 辅助
理解与压缩之间存在何种关系，为何人类理解会呈现出高度压缩的形式？在信息论、机器学习与AI研究领域，有大量研究将理解等同于压缩，格雷戈里·蔡廷的格言“理解即压缩”便体现了这一观点。而哲学家则从把握关联、给出解释和处理新事物的角度来定义理解。本文通过三个相互关联的论点弥合了这两种观点：第一，关于理解的概念，它是一种独特的稳健能力的高效代理，使我们能够确定信任谁、向谁学习；第二，关于理解的状态，理解一个领域即拥有该领域关系结构的心智模型，该模型可用于预测，而能预测的事物无需单独存储，因此能实现压缩，压缩并非理解本身，而是其表征的影子；第三，关于人类理解的特征，第一个论点强调的信托与传递功能，对可展示性和可传递性施加了压力，推动人类理解趋向原则性的简洁。该框架解释了压缩主义理解理论的吸引力与局限性，同时阐明了AI系统的不可解释性。
英文摘要
What is the relation between understanding and compression, and why does human understanding take such a heavily compressed form? Across information theory, machine learning, and AI research, a substantial tradition identifies understanding with compression-a thought captured in Gregory Chaitin's dictum that "comprehension is compression." Philosophers, by contrast, have characterized understanding in terms of grasping connections, giving explanations, and handling novelty. This paper bridges the two pictures through three interlocking theses. The first concerns the concept of understanding: it serves as an efficient proxy for a distinctive form of robust competence, enabling us to identify whom to trust and whom to learn from. The second concerns the state of understanding: to understand a domain is to possess a mental model of its relational structure that enables prediction, and what enables prediction enables compression, because what becomes predictable need not be stored separately. Compression is therefore not identical with comprehension, but its representational shadow. The third concerns the characteristically human form of understanding: the fiduciary and transmission functions highlighted by the first thesis impose pressures of demonstrability and transmissibility that drive human understanding toward principled simplicity. The resulting framework explains both the appeal and the limits of compressionist accounts of understanding while shedding light on the inscrutability of AI systems.
