按年被提到
20232026 · 2 次2026
AI 安全、伦理与社会影响›通用智能与意识·arXiv:2301.12987 · cs.AI

The Optimal Choice of Hypothesis Is the Weakest, Not the Shortest

Michael Timothy Bennett · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2024-01-26 · 最近 2026-08-05
3不同的人
2活跃月份
3讨论串
25被引(OpenAlex)
arXiv 摘要(候选层不写导读)

If $A$ and $B$ are sets such that $A \subset B$, generalisation may be understood as the inference from $A$ of a hypothesis sufficient to construct $B$. One might infer any number of hypotheses from $A$, yet only some of those may generalise to $B$. How can one know which are likely to generalise? One strategy is to choose the shortest, equating the ability to compress information with the ability to generalise (a proxy for intelligence). We examine this in the context of a mathematical formalism of enactive cognition. We show that compression is neither necessary nor sufficient to maximise performance (measured in terms of the probability of a hypothesis generalising). We formulate a proxy unrelated to length or simplicity, called weakness. We show that if tasks are uniformly distributed, then there is no choice of proxy that performs at least as well as weakness maximisation in all tasks while performing strictly better in at least one. In experiments comparing maximum weakness and minimum description length in the context of binary arithmetic, the former generalised at between $1.1$ and $5$ times the rate of the latter. We argue this demonstrates that weakness is a far better proxy, and explains why Deepmind's Apperception Engine is able to generalise effectively.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论jabowery · 2024-01

“This recent paper provides one of two rigorous measures (with code) of machine intelligence that could be used to discipline discourse about "AGI". The other (with code) is a seminal paper by Shane Legg and Joel Veness "An Approximation of the Universal Intelligence Measure".”

The Optimal Choice of Hypothesis Is the Weakest, Not the Shortest原评论 ↗
被提交为 story · 3 次