PulseAugur
中
实时 12:29:30

Research links neural networks, ODEs, and polynomial maps to primitive recursion

作者 PulseAugur 编辑部 · [2 个来源] ·

A new paper explores the computational capabilities of recurrent neural networks, polynomial ordinary differential equations (ODEs), and discrete polynomial maps. The research establishes equivalent characterizations for primitive recursion across these frameworks, demonstrating how composition emerges from dynamics rather than explicit closure rules. This work offers dynamical characterizations of complexity classes by analyzing time bounds, polynomial degrees, and discretization resources. AI

影响 Provides a theoretical framework for understanding computation in dynamical systems, potentially influencing future AI architectures.

排序理由 Academic paper detailing theoretical computational equivalences.

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Research links neural networks, ODEs, and polynomial maps to primitive recursion

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Olivier Bournez ·

    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…

  2. arXiv cs.LG TIER_1 English(EN) · Olivier Bournez ·

    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 …

相关实体

相关话题