How do PDP models learn quasiregularity?
How do PDP models learn quasiregularity?
复制标题
PDP 模型如何学习拟正则性？
DOI：
10.1037/a0034195
复制
发表时间：
2013
影响因子：
5.4
通讯作者：
Myung,JayI
中科院分区：
文献类型：
--
作者：
Kim,Woojae;Pitt,MarkA;Myung,JayI
并行分布式处理（PDP）模型对认知研究产生了深远的影响。他们特别有影响力的一个领域是学习准规律性，其中掌握需要学习捕获输入中大部分结构的规律性以及学习违反规律性的异常。 PDP 模型如何学习拟正则性仍不清楚。对前馈 3 层网络进行小规模和大规模分析，以解决有关网络功能的 2 个基本问题：模型如何在不牺牲泛化性的情况下学习规律和异常，以及使这种学习成为可能的隐藏表示的性质。结果表明，容量有限的学习迫使网络形成成分表示，从而确保良好的泛化性。这种表征系统的小而高度局部的扰动允许在最小限度地破坏泛化性的同时学习例外情况。讨论了研究结果的理论和方法学意义。
Parallel distributed processing (PDP) models have had a profound impact on the study of cognition. One domain in which they have been particularly influential is learning quasiregularity, in which mastery requires both learning regularities that capture the majority of the structure in the input plus learning exceptions that violate the regularities. How PDP models learn quasiregularity is still not well understood. Small-and large-scale analyses of a feedforward, 3-layer network were carried out to address 2 fundamental issues about network functioning: how the model can learn both regularities and exceptions without sacrificing generalizability and the nature of the hidden representation that makes this learning possible. Results show that capacity-limited learning pressures the network to form componential representations, which ensures good generalizability. Small and highly local perturbations of this representational system allow exceptions to be learned while minimally disrupting generalizability. Theoretical and methodological implications of the findings are discussed.