Rules and Similarity in Concept Learning

Rules and Similarity in Concept Learning
复制标题

概念学习中的规则和相似性

DOI:
--
复制
发表时间:
1999
期刊:
Neural Information Processing Systems
影响因子:
--
通讯作者:
J. Tenenbaum
J. Tenenbaum
中科院分区:
--
文献类型:
--
作者:
J. Tenenbaum

文献摘要

参考文献

被引文献

相似文献

本文认为概括概念的两种明显不同的模式——抽象规则和计算与范例的相似性——都应该被视为更一般的贝叶斯学习框架的特殊情况。贝叶斯解释了这两种模式的具体工作原理——哪些规则是抽象的,相似性是如何测量的——以及为什么泛化应该在不同的情况下以规则或相似性为基础。这个分析也说明了为什么规则/相似性的区别,即使不是计算基础,在算法层面上仍然是有用的,作为完全贝叶斯学习的原则近似的一部分。
This paper argues that two apparently distinct modes of generalizing concepts - abstracting rules and computing similarity to exemplars - should both be seen as special cases of a more general Bayesian learning framework. Bayes explains the specific workings of these two modes - which rules are abstracted, how similarity is measured - as well as why generalization 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.
类别学习的规则和范例。
DOI: 10.1037//0096-3445.127.2.107
发表时间: 1998
期刊: Journal of experimental psychology. General.
影响因子: --
作者:
Erickson,MA;Kruschke,JK
通讯作者: Kruschke,JK