Learning the generative principles of a symbol system from limited examples

Learning the generative principles of a symbol system from limited examples
复制标题

从有限的例子中学习符号系统的生成原理

DOI:
10.1016/j.cognition.2020.104243
复制
发表时间:
2020
期刊:
影响因子:
3.4
通讯作者:
Smith, Linda
Smith, Linda
中科院分区:
心理学2区
文献类型:
--
作者:
Yuan, Lei;Xiang, Violet;Crandall, David;Smith, Linda

文献摘要

参考文献

被引文献

相似文献

人类学习的过程和机制是心理学、认知科学、发展、教育和人工智能等许多领域研究的核心。争论、争论和争议在人类学习的问题上挥之不去,其中最有争议的是简单的联想过程是否可以解释人类儿童惊人的学习能力,并且在这样做的过程中,可能会导致与人类学习相似的人工智能。在这些争论的中心的一个现象涉及到一种形式的远泛化,有时被称为“生成学习”,因为学习者的行为似乎反映了更多的共同出现之间的具体经验的情况下,并根据原则,通过新的实例可能begenerated。在两项关于学龄前儿童学习多位数字名称如何映射到其书面形式的实验研究(N= 148)中,以及在使用深度学习神经网络的计算建模实验中,我们发现,数据集与一套间-相关的不完美预测分量产生远的和系统的概括,其雅阁生成原理,并且尽管训练数据中的有限示例和例外也是如此。对人类认知,认知发展,教育和机器学习的影响进行了讨论。
The processes and mechanisms of human learning are central to inquiries in a number of fields including psychology, cognitive science, development, education, and artificial intelligence. Arguments, debates, and controversies linger over the questions of human learning with one of the most contentious being whether simple associative processes could explain human children's prodigious learning, and in doing so, could lead to artificial intelligence that parallels human learning. One phenomenon at the center of these debates concerns a form of far generalization, sometimes referred to as “generative learning”, because the learner's behavior seems to reflect more than co-occurrences among specifically experienced instances and to be based on principles through which new instances may begenerated. In two experimental studies (N= 148) of preschool children's learning of how multi-digit number names map to their written forms and in a computational modeling experiment using a deep learning neural network, we show that data sets with a suite of inter-correlated imperfect predictive components yield far and systematic generalizations that accord with generative principles and do so despite limited examples and exceptions in the training data. Implications for human cognition, cognitive development, education, and machine learning are discussed.
DOI: 10.1073/pnas.1303312110
发表时间: 2013-08-27
影响因子: 11.1
作者:
Lupyan, Gary;Ward, Emily J.
通讯作者: Ward, Emily J.
DOI: 10.1016/j.jecp.2012.08.002
发表时间: 2012-12-01
影响因子: 2.6
作者:
Mann, Anne;Moeller, Korbinian;Nuerk, Hans-Christoph
通讯作者: Nuerk, Hans-Christoph
受幼儿启发的视觉对象学习
DOI: --
发表时间: 2018
期刊: Neural Information Processing Systems
影响因子: --
作者:
S. Bambach;David J. Crandall;Linda B. Smith;Chen Yu
通讯作者: Chen Yu
DOI: 10.1016/0010-0277(92)90030-l
发表时间: 1992-04-01
期刊: COGNITION
影响因子: 3.4
作者:
DEHAENE, S;MEHLER, J
通讯作者: MEHLER, J
DOI: --
发表时间: 2012
期刊:
影响因子: --
作者:
M. Chi;Agnieszka Kosminska M. Kristensen;Rod D. Roscoe
通讯作者: Rod D. Roscoe