Part of Advances in Neural Information Processing Systems 12 (NIPS 1999)
Joshua Tenenbaum
This paper argues that two apparently distinct modes of generalizing con(cid:173) cepts - abstracting rules and computing similarity to exemplars - should both be seen as special cases of a more general Bayesian learning frame(cid:173) work. Bayes explains the specific workings of these two modes - which rules are abstracted, how similarity is measured - as well as why gener(cid:173) alization should appear rule- or similarity-based in different situations. This analysis also suggests why the rules/similarity distinction, even if not computationally fundamental, may still be useful at the algorithmic level as part of a principled approximation to fully Bayesian learning.