arXiv:2609.04528cs.AIcs.PL2026-09综述
用程序作为概念的通用表达，让机器也能像人一样从少量数据中理解新概念。
Towards a universal language of concepts: A survey
- 以程序为概念载体，构建可泛化的知识表示
- 综述了多种基于程序的概念学习模型
- 适合对通用认知模型和符号学习感兴趣的读者
人类能从少量数据中学习并泛化新概念，是因为他们以丰富的结构化方式表达知识。本文提出，程序是概念通用表征的有力候选。我们回顾了使用程序作为概念表示的计算模型，并评估其在构建通用表征语言方面的贡献。
原文摘要 · Abstract (English)
Humans can learn and generalize novel concepts from sparse data because they express knowledge in rich structural formats. In this paper, we propose that programs are a strong candidate for universal representation of concepts. We review computational models of concept learning that use programs as their concept representation and evaluate their contribution toward a universal representational language.
概念学习程序表征通用语言
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。