arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2509.03370cs.NEcs.AI
收藏

神经场图灵机:一种可微空间计算机

Neural Field Turing Machine: A Differentiable Spatial Computer

Akash Malhotra, Nacéra Seghouani

AI总结:

本研究提出可微架构神经场图灵机(NFTM),结合神经控制器、连续记忆场与可移动读写头,实现线性扩展且保持图灵完备性,在元胞自动机模拟、PDE求解和图像修复任务中验证了其长时稳定推演与泛化能力,为统一离散算法与连续场动力学提供了计算基底。

摘要:

我们提出神经场图灵机(Neural Field Turing Machine,NFTM),这是一种可微架构,在连续空间场中统一了符号计算、物理模拟与感知推理。NFTM 结合了神经控制器、连续记忆场以及可执行局部更新的可移动读写头。在每个时间步,控制器读取局部补丁,通过学习到的规则计算更新,并将其写回,同时更新读写头位置。该设计通过固定半径邻域实现线性 O(N) 扩展性,同时在有界误差下保持图灵完备性。我们展示了 NFTM 的三个示例实例:元胞自动机模拟(Rule 110)、物理信息驱动的偏微分方程(PDE)求解器(二维热方程)以及迭代图像细化(CIFAR-10 图像修复)。这些实例学习到的局部更新规则可组合为全局动力学,展现出稳定的长时程推演能力,且能泛化到训练时域之外。NFTM 提供了一种统一的计算基底,在单一可微框架内架起了离散算法与连续场动力学之间的桥梁。

英文摘要:

We introduce the Neural Field Turing Machine (NFTM), a differentiable architecture that unifies symbolic computation, physical simulation, and perceptual inference within continuous spatial fields. NFTM combines a neural controller, continuous memory field, and movable read/write heads that perform local updates. At each timestep, the controller reads local patches, computes updates via learned rules, and writes them back while updating head positions. This design achieves linear O(N) scaling through fixed-radius neighborhoods while maintaining Turing completeness under bounded error. We demonstrate three example instantiations of NFTM: cellular automata simulation (Rule 110), physics-informed PDE solvers (2D heat equation), and iterative image refinement (CIFAR-10 inpainting). These instantiations learn local update rules that compose into global dynamics, exhibit stable long-horizon rollouts, and generalize beyond training horizons. NFTM provides a unified computational substrate bridging discrete algorithms and continuous field dynamics within a single differentiable framework.

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。

↑