Probabilistic programming versus meta-learning as models of cognition
Desmond C. Ong, Tan Zhi‐Xuan, Joshua B. Tenenbaum, Noah D. Goodman · Behavioral and Brain Sciences · 2024
Abstract 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.