… We provide a visualization demonstrating that the predictions of a meta-learned model
closely resemble those of exact Bayesian inference for our insect length example in Figures 3c …

… the long-standing goal of a general model of cognition. Overall we see meta-learned models
of cognition as not supplanting existing cognitive models, but as a way to make them much …

… Within cognitive science, hierarchical Bayesian models of cognition capture how learning …
-learning method, model-agnostic meta-learning [36 •• ], in which what is meta-learned are the …

… I propose that meta-learned models, and in particular the situation-aware deployment of “…
domains commonly thought to lie outside the cognitive, such as motivations and preferences on …

… ) allow us to model how people invoke modeling and inference … meta-learned inference
when one believes a familiar model applies, but also flexibly compute inferences when a model …

… model uncertainty quantification. To this end, we propose a novel Bayesian mETAlearned
Cognitive … We first introduce Bayesian hierarchical modeling for the cognitive diagnosis task. …

… These phenomena are readily explained by the compositionality of classical cognitive
architectures, as the design of their symbolic representations and structure-sensitive operations …

… In this work, we suggest bounded meta-learned inference (BMI) as a novel computational …
cost relates to other costs commonly used in cognitive science in the General Discussion. …

… accounts provided by models of adaptive reinforcement … lens of models of meta-learning —
and models of meta-reinforcement learning in particular. Meta-reinforcement learning models …

… While we have suggested that researchers can leverage meta-learned models to more
explicitly test … Meta-learned models of cognition thus have the potential to address questions of …