Towards a universal language of concepts: A survey
arXiv:2609.04528
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.
Originally completed as an M.S. capstone project at UCLA in 2022