一篇新论文探讨了循环神经网络、多项式常微分方程（ODEs）和离散多项式映射的计算能力。该研究在这些框架中建立了原始递归的等价刻画，展示了组合如何从动力学而非显式闭包规则中涌现。这项工作通过分析时间界限、多项式次数和离散化资源，为复杂性类提供了动力学刻画。 AI
影响 为理解动力学系统中的计算提供了一个理论框架，可能影响未来的AI架构。
排序理由 学术论文，详细介绍了理论计算等价性。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
研究将神经网络、常微分方程和多项式映射与原始递归联系起来
报道来源 [2]
-
Primitive Recursion without Composition: Dynamical Characterizations, from Neural Networks to Polynomial ODEs
arXiv:2604.24356v1 Announce Type: cross Abstract: What do recurrent neural networks, polynomial ODEs, and discrete polynomial maps each bring to computation, and what do they lack? All three operate over the continuum--real-valued states evolved by real-valued dynamics--even when…
-
Primitive Recursion without Composition: Dynamical Characterizations, from Neural Networks to Polynomial ODEs
What do recurrent neural networks, polynomial ODEs, and discrete polynomial maps each bring to computation, and what do they lack? All three operate over the continuum--real-valued states evolved by real-valued dynamics--even when the target functions are discrete. We study them …