用神经元细胞自动机解决抽象推理任务，展现少样本泛化能力
Neural Cellular Automata for ARC-AGI
- 通过梯度训练学习网格迭代更新规则
- 在ARC-AGI上实现高效准确的抽象变换
- 适合研究自组织系统与通用智能的探索者
细胞自动机及其可微分变体——神经细胞自动机（NCA）具有高度表达性，能产生复杂行为。本文将NCA应用于需要精确变换和少样本泛化能力的挑战性任务，以人工智能通用智能抽象推理数据集（ARC-AGI）为测试场景，探索其未被充分研究的能力。具体而言，采用基于梯度的训练方法，从训练样本中学习将输入网格转换为输出网格的迭代更新规则，并将其应用于测试输入。结果表明，梯度训练的NCA模型是应对一系列基于网格的抽象任务的有效且高效的方法。本文还分析了不同设计修改与训练约束的影响，考察了NCA在处理ARC任务时的行为特性，为自组织系统的更广泛应用提供洞见。
原文摘要 · Abstract (English)
Cellular automata and their differentiable counterparts, Neural Cellular Automata (NCA), are highly expressive and capable of surprisingly complex behaviors. This paper explores how NCAs perform when applied to tasks requiring precise transformations and few-shot generalization, using the Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) as a domain that challenges their capabilities in ways not previously explored. Specifically, this paper uses gradient-based training to learn iterative update rules that transform input grids into their outputs from the training examples and apply them to the test inputs. Results suggest that gradient-trained NCA models are a promising and efficient approach to a range of abstract grid-based tasks from ARC. Along with discussing the impacts of various design modifications and training constraints, this work examines the behavior and properties of NCAs applied to ARC to give insights for broader applications of self-organizing systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。