Towards a universal language of concepts: A survey
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 7 of its 43 references that are in the map. First posted on arXiv 3 Sep 2026.
Builds on
7 of 43 references.
References · 7
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
- 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 369
- 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 159
- 2018HOUDINI: Lifelong Learning as Program Synthesiscited by 38
- 2018Solving Bongard Problems with a Visual Language and Pragmatic Reasoningcited by 21
- 2018Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programscited by 21
- 2018Representational efficiency outweighs action efficiency in human program inductioncited by 4
Built on by
Not cited yet.