Towards a universal language of concepts: A survey

2026-09-03

AI Summary

本文探讨使用程序作为概念的通用表示方法，以解决人类如何从稀疏数据中学习和泛化新概念的问题。

Abstract

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.

Problem

• universal representation
• concept learning
• programs

Innovation

• programs
• concept representation
• universal language