Tenenbaum Joshua B, Griffiths Thomas L, Kemp Charles
Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA, USA.
Trends Cogn Sci. 2006 Jul;10(7):309-18. doi: 10.1016/j.tics.2006.05.009. Epub 2006 Jun 22.
Inductive inference allows humans to make powerful generalizations from sparse data when learning about word meanings, unobserved properties, causal relationships, and many other aspects of the world. Traditional accounts of induction emphasize either the power of statistical learning, or the importance of strong constraints from structured domain knowledge, intuitive theories or schemas. We argue that both components are necessary to explain the nature, use and acquisition of human knowledge, and we introduce a theory-based Bayesian framework for modeling inductive learning and reasoning as statistical inferences over structured knowledge representations.
归纳推理使人类在学习词义、未观察到的属性、因果关系以及世界的许多其他方面时，能够从稀疏数据中做出有力的概括。传统的归纳解释要么强调统计学习的力量，要么强调结构化领域知识、直观理论或图式的强约束的重要性。我们认为，这两个组成部分对于解释人类知识的本质、使用和获取都是必要的，并且我们引入了一个基于理论的贝叶斯框架，将归纳学习和推理建模为对结构化知识表示的统计推断。
