Towards a universal language of concepts: A survey

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

Artificial Intelligence (cs.AI); Programming Languages (cs.PL); Symbolic Computation (cs.SC)

arXiv:2609.04528 [cs.AI]

(or arXiv:2609.04528v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.04528 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.