Learning overhypotheses with hierarchical Bayesian models.

  title={Learning overhypotheses with hierarchical Bayesian models.},
  author={Charles Kemp and Amy Perfors and Joshua B. Tenenbaum},
  journal={Developmental science},
  volume={10 3},
Inductive learning is impossible without overhypotheses, or constraints on the hypotheses considered by the learner. Some of these overhypotheses must be innate, but we suggest that hierarchical Bayesian models can help to explain how the rest are acquired. To illustrate this claim, we develop models that acquire two kinds of overhypotheses--overhypotheses… CONTINUE READING