研究人员详细介绍了一个最小神经网络系统（具体为一个192维GRU）中人工能动性的发展路径。该研究概述了一个预测系统区分自我引起的行为与外部事件所必需的四个顺序条件。这些条件包括稳定状态、因果行动循环、本体感觉反馈和异步学习，并提出能动性增益作为关键指标。 AI
影响 为在AI系统中发展能动性建立了理论框架和指标，可能指导未来具身AI和自我意识代理的研究。
排序理由 该集群包含一篇研究论文，详细介绍了一种在神经网络中发展能动性的新方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.05605v1 Announce Type: new Abstract: How does a system that merely predicts the world come to distinguish its own causal influence from everything else? We trace this transition in a minimal 192-dimensional GRU through 40 controlled experiments arranged as a developmen…
How does a system that merely predicts the world come to distinguish its own causal influence from everything else? We trace this transition in a minimal 192-dimensional GRU through 40 controlled experiments arranged as a developmental sequence, adding components one at a time an…