Quinn P C, Johnson M H
Department of Psychology, Washington and Jefferson College, Washington, PA 15301, USA.
J Exp Child Psychol. 1997 Aug;66(2):236-63. doi: 10.1006/jecp.1997.2385.
There has been recent interest in the idea that principles governing learning in connectionist networks can form the basis for an alternative understanding of developmental processes (Elman, Bates, Karmiloff-Smith, Johnson, Parisi, & Plunkett, 1996). The present paper can be viewed as a case example of the usefulness (and limitations) of connectionist modeling for the study of infant cognition. Specifically, the paper reports on a series of connectionist models designed to analyze the factors responsible for the emergence of global-level and basic-level category representations in young infants. The models (1) simulated the formation of global-level and basic-level representations, (2) revealed a global-to-basic order of category emergence, (3) uncovered the formation of two distinct global-level representations-an initial "self-organizing" perceptual global level and a subsequently "trained" arbitrary (i.e., nonperceptual) global level, and (4) displayed a gradual transition from perceptual global-level to perceptual basic-level representation with increasing exposure to training stimuli. Hypotheses for empirical investigations of category development in infants that follow from the modeling efforts are discussed.
最近,人们对一种观点产生了兴趣,即连接主义网络中的学习原则可以为理解发展过程提供另一种基础(埃尔曼、贝茨、卡米洛夫-史密斯、约翰逊、帕里西和普伦基特,1996)。本文可被视为连接主义建模在婴儿认知研究中的有用性(和局限性)的一个案例。具体而言,本文报告了一系列连接主义模型,这些模型旨在分析导致幼儿出现全局水平和基本水平类别表征的因素。这些模型(1)模拟了全局水平和基本水平表征的形成,(2)揭示了类别出现的全局到基本的顺序,(3)发现了两种不同全局水平表征的形成——最初的“自组织”感知全局水平和随后的“训练”任意(即非感知)全局水平,以及(4)随着接触训练刺激的增加,显示出从感知全局水平到感知基本水平表征的逐渐转变。讨论了基于建模工作得出的关于婴儿类别发展实证研究的假设。