arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.04430cs.AI
收藏

人工通用智能的基础要求:一个基于信号预测的可证伪框架

Foundational Requirements for Artificial General Intelligence: A Falsifiable Framework Based on Signal Prediction

University of Maribor, Faculty of Electrical Engineering and Computer Science(马里博大学电子工程与计算机科学学院)

Matej Šprogar

AI总结:

本文提出一个基于信号预测的可证伪框架,通过定义低层要求(如从无知状态学习、实时活性)并设计可重复测试来检验人工通用智能。

摘要:

基于高级智能可以从低级信号处理中涌现的前提,我们提出了关于人工通用智能所需的低级要求的假设。所提出的要求刻画了通过预测具有初始未知语义内容的时空结构化信号进行学习的系统的核心属性。它们包括从认知神经科学中观察到的基本原理,从从无知状态学习到实时活性。为了进行实证检验和假设拒绝,我们引入了一个由透明且可重复的测试组成的操作测试平台,每个要求对应一个测试。迄今为止,尚未发现或报告有任何非智能系统成功通过该测试平台。在出现这样的反例之前,该测试平台可作为通向通用智能的候选实证里程碑。该测试平台的参考实现已公开可用。

英文摘要:

Grounded in the premise that high-level intelligence can emerge from low-level signal processing, we hypothesise a set of requirements necessary for artificial general intelligence. They characterise systems that learn by predicting spatially and temporally structured signals of initially unknown meaning, and draw on principles observed in cognitive neuroscience, from learning from an uninformed state to real-time liveness. To enable empirical testing and rejection of the hypothesis, we introduce a testbed of transparent, reusable tests, one per requirement. Failing a test exposes a violation of a requirement, but passing is not conclusive: a transparent testbed cannot detect systems engineered around its tests, and such systems can pass it without being intelligent. Passing is therefore meaningful only for systems developed without knowledge of the tests, and none has yet been reported. The testbed thus serves as a necessary-condition filter rather than as proof of progress toward general intelligence. Its reference implementation is publicly available.

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。

↑