Towards a universal language of concepts: A survey
Aishni Parab
cs.AI cs.PL cs.SC
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.
Topics
Classified with taxonomy v2 on Mon, 7 Sept 2026.