自组织数字电路
Self-Organising Digital Circuits
浏览论文内容
中文总结 AI 辅助
该研究受生物自组织特性启发，提出自组织数字电路，采用拓扑掩码Transformer结合神经细胞自动机范式，实现电路的自组装与故障容错，还具备跨电路规模的泛化能力。
中文摘要 AI 辅助
传统经典计算中的容错性依赖硬件冗余、纠错码等静态策略，而生物系统展现出自适应可塑性，能通过损伤周围的动态重组维持功能。受此启发，本文提出自组织数字电路，将功能逻辑的生成与维护视为图上的元学习问题。该架构采用拓扑掩码Transformer，配置电路布尔门的查找表（LUT）；扩展神经细胞自动机（NCA）的模式生成范式，在退化的布尔搜索空间中导航以满足计算任务，而非再生固定目标状态。实验表明，该模型可从头自组装功能电路，能快速绕开此前未见过的永久性硬件故障重新路由逻辑；对于软错误，在损伤规模远超训练条件时，策略实现近完美恢复（准确率>99.99%）；还观察到电路规模上的泛化性：在比训练时宽得多的图上准确率提升。本研究将生物自组织原理与数字硬件的实际领域相结合。
英文摘要
Fault tolerance in classical computing has traditionally relied on static strategies like hardware redundancy and error-correcting codes. Biological systems, in contrast, exhibit adaptive plasticity, maintaining function through dynamic re-organisation around damage. Inspired by this principle, we introduce Self-Organising Digital Circuits, framing functional logic generation and maintenance as a meta-learning problem on graphs. Our architecture employs a topology-masked Transformer that configures the Lookup Tables (LUT) of a circuit's Boolean gates. Extending the pattern-generation paradigm of Neural Cellular Automata (NCA), it navigates the degenerate Boolean search space to satisfy a computational task, rather than regenerating a fixed target state. We demonstrate that it can self-assemble functional circuits from scratch and rapidly re-route logic around permanent, previously unseen hardware faults. For soft errors, the policy achieves near-perfect recovery (>99.99\% accuracy) from damage sizes far exceeding training conditions. We further observe generalisation across circuit scales: accuracy improves on graphs substantially wider than those seen during training. This work bridges the principles of biological self-organisation with the practical domain of digital hardware.
发表机构
- IT University of Copenhagen（哥本哈根信息技术大学）
- Imperial College London（帝国理工学院）
- Google（谷歌公司）
机构由 AI 辅助整理，请以论文原文为准。
