Structured statistical models of inductive reasoning. Kemp, C. & Tenenbaum, J. B Psychol Rev, 116(1):20–58, 2009. doi abstract bibtex Everyday inductive inferences are often guided by rich background knowledge. Formal models of induction should aim to incorporate this knowledge and should explain how different kinds of knowledge lead to the distinctive patterns of reasoning found in different inductive contexts. This article presents a Bayesian framework that attempts to meet both goals and describes [corrected] 4 applications of the framework: a taxonomic model, a spatial model, a threshold model, and a causal model. Each model makes probabilistic inferences about the extensions of novel properties, but the priors for the 4 models are defined over different kinds of structures that capture different relationships between the categories in a domain. The framework therefore shows how statistical inference can operate over structured background knowledge, and the authors argue that this interaction between structure and statistics is critical for explaining the power and flexibility of human reasoning.
@Article{Kemp2009,
author = {Charles Kemp and Joshua B Tenenbaum},
journal = {Psychol Rev},
title = {Structured statistical models of inductive reasoning.},
year = {2009},
number = {1},
pages = {20--58},
volume = {116},
abstract = {Everyday inductive inferences are often guided by rich background
knowledge. Formal models of induction should aim to incorporate this
knowledge and should explain how different kinds of knowledge lead
to the distinctive patterns of reasoning found in different inductive
contexts. This article presents a Bayesian framework that attempts
to meet both goals and describes [corrected] 4 applications of the
framework: a taxonomic model, a spatial model, a threshold model,
and a causal model. Each model makes probabilistic inferences about
the extensions of novel properties, but the priors for the 4 models
are defined over different kinds of structures that capture different
relationships between the categories in a domain. The framework therefore
shows how statistical inference can operate over structured background
knowledge, and the authors argue that this interaction between structure
and statistics is critical for explaining the power and flexibility
of human reasoning.},
doi = {10.1037/a0014282},
keywords = {Association Learning; Bayes Theorem; Concept Formation; Decision Making; Humans; Judgment; Knowledge; Mental Recall; Models, Statistical; Neural Networks (Computer); Problem Solving; Psychological Theory},
language = {eng},
medline-pst = {ppublish},
pmid = {19159147},
school = {Department of Psychology, Carnegie Mellon University. ckemp@cmu.edu},
timestamp = {2011.05.10},
}
Downloads: 0
{"_id":"8ocj3xw4DfaLrJynD","bibbaseid":"kemp-tenenbaum-structuredstatisticalmodelsofinductivereasoning-2009","author_short":["Kemp, C.","Tenenbaum, J. B"],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Charles"],"propositions":[],"lastnames":["Kemp"],"suffixes":[]},{"firstnames":["Joshua","B"],"propositions":[],"lastnames":["Tenenbaum"],"suffixes":[]}],"journal":"Psychol Rev","title":"Structured statistical models of inductive reasoning.","year":"2009","number":"1","pages":"20–58","volume":"116","abstract":"Everyday inductive inferences are often guided by rich background knowledge. Formal models of induction should aim to incorporate this knowledge and should explain how different kinds of knowledge lead to the distinctive patterns of reasoning found in different inductive contexts. This article presents a Bayesian framework that attempts to meet both goals and describes [corrected] 4 applications of the framework: a taxonomic model, a spatial model, a threshold model, and a causal model. Each model makes probabilistic inferences about the extensions of novel properties, but the priors for the 4 models are defined over different kinds of structures that capture different relationships between the categories in a domain. The framework therefore shows how statistical inference can operate over structured background knowledge, and the authors argue that this interaction between structure and statistics is critical for explaining the power and flexibility of human reasoning.","doi":"10.1037/a0014282","keywords":"Association Learning; Bayes Theorem; Concept Formation; Decision Making; Humans; Judgment; Knowledge; Mental Recall; Models, Statistical; Neural Networks (Computer); Problem Solving; Psychological Theory","language":"eng","medline-pst":"ppublish","pmid":"19159147","school":"Department of Psychology, Carnegie Mellon University. ckemp@cmu.edu","timestamp":"2011.05.10","bibtex":"@Article{Kemp2009,\n author = {Charles Kemp and Joshua B Tenenbaum},\n journal = {Psychol Rev},\n title = {Structured statistical models of inductive reasoning.},\n year = {2009},\n number = {1},\n pages = {20--58},\n volume = {116},\n abstract = {Everyday inductive inferences are often guided by rich background\n\tknowledge. Formal models of induction should aim to incorporate this\n\tknowledge and should explain how different kinds of knowledge lead\n\tto the distinctive patterns of reasoning found in different inductive\n\tcontexts. This article presents a Bayesian framework that attempts\n\tto meet both goals and describes [corrected] 4 applications of the\n\tframework: a taxonomic model, a spatial model, a threshold model,\n\tand a causal model. Each model makes probabilistic inferences about\n\tthe extensions of novel properties, but the priors for the 4 models\n\tare defined over different kinds of structures that capture different\n\trelationships between the categories in a domain. The framework therefore\n\tshows how statistical inference can operate over structured background\n\tknowledge, and the authors argue that this interaction between structure\n\tand statistics is critical for explaining the power and flexibility\n\tof human reasoning.},\n doi = {10.1037/a0014282},\n keywords = {Association Learning; Bayes Theorem; Concept Formation; Decision Making; Humans; Judgment; Knowledge; Mental Recall; Models, Statistical; Neural Networks (Computer); Problem Solving; Psychological Theory},\n language = {eng},\n medline-pst = {ppublish},\n pmid = {19159147},\n school = {Department of Psychology, Carnegie Mellon University. ckemp@cmu.edu},\n timestamp = {2011.05.10},\n}\n\n","author_short":["Kemp, C.","Tenenbaum, J. B"],"key":"Kemp2009","id":"Kemp2009","bibbaseid":"kemp-tenenbaum-structuredstatisticalmodelsofinductivereasoning-2009","role":"author","urls":{},"keyword":["Association Learning; Bayes Theorem; Concept Formation; Decision Making; Humans; Judgment; Knowledge; Mental Recall; Models","Statistical; Neural Networks (Computer); Problem Solving; Psychological Theory"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://endress.org/publications/ansgar.bib","dataSources":["xPGxHAeh3vZpx4yyE","TXa55dQbNoWnaGmMq"],"keywords":["association learning; bayes theorem; concept formation; decision making; humans; judgment; knowledge; mental recall; models","statistical; neural networks (computer); problem solving; psychological theory"],"search_terms":["structured","statistical","models","inductive","reasoning","kemp","tenenbaum"],"title":"Structured statistical models of inductive reasoning.","year":2009}