Theory-based Bayesian models of inductive learning and reasoning

@article{Tenenbaum.2006, abstract = {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.}, author = {Tenenbaum, Joshua B. and Griffiths, Thomas L. and Kemp, Charles }, citeulike-article-id = {2860114}, doi = {http://dx.doi.org/10.1016/j.tics.2006.05.009}, journal = {Trends in Cognitive Sciences}, number = {7}, posted-at = {2008-06-04 00:53:30}, priority = {2}, title = {Theory-based Bayesian models of inductive learning and reasoning}, url = {http://dx.doi.org/10.1016/j.tics.2006.05.009}, volume = {10}, year = {2006} }

TY - JOUR ID - Tenenbaum.2006 L3 - citeulike-article-id:2860114 TI - Theory-based Bayesian models of inductive learning and reasoning JF - Trends in Cognitive Sciences VL - 10 IS - 7 N2 - 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. AU - Tenenbaum, Joshua AU - Griffiths, Thomas AU - Kemp, Charles PY - 2006/// UR - http://dx.doi.org/10.1016/j.tics.2006.05.009 ER -