Probabilistic programming versus meta-learning as models of cognition.
Desmond C OngTan Zhi-XuanJoshua B TenenbaumNoah D GoodmanPublished in: The Behavioral and brain sciences (2024)
We summarize the recent progress made by probabilistic programming as a unifying formalism for the probabilistic, symbolic, and data-driven aspects of human cognition. We highlight differences with meta-learning in flexibility, statistical assumptions and inferences about cogniton. We suggest that the meta-learning approach could be further strengthened by considering Connectionist and Bayesian approaches, rather than exclusively one or the other.