LEARNING AND DEVELOPMENT IN NEURAL NETWORKS - THE IMPORTANCE OF STARTING SMALL
LEARNING AND DEVELOPMENT IN NEURAL NETWORKS - THE IMPORTANCE OF STARTING SMALL
复制标题
DOI：
10.1016/0010-0277(93)90058-4
复制
发表时间：
1993-07-01
期刊：
影响因子：
3.4
通讯作者：
ELMAN, JL
中科院分区：
文献类型：
--
作者：
ELMAN, JL
这是一个惊人的事实，在人类中，最大的学习精确发生在那个时间点 - 童年时期 - 当时也发生了最戏剧性的成熟变化。本报告描述了成熟变化与学习复杂领域（语言）的能力之间可能的协同互动，如在连接主义网络中所研究。对网络进行了训练，以处理涉及相对子句，数字一致性和几种类型的动词参数结构的复杂句子。培训失败的是完全形成和以其身份“成人”的网络。培训仅在网络以有限的工作记忆开始并逐渐“成熟”到成年状态时才能成功。该结果表明，对资源的发展限制不是限制，可能构成掌握某些复杂领域的必要先决条件。具体而言，成功的学习可能取决于开始小。
It is a striking fact that in humans the greatest learning occurs precisely at that point in time - childhood - when the most dramatic maturational changes also occur. This report describes possible synergistic interactions between maturational change and the ability to learn a complex domain (language), as investigated in connectionist networks. The networks are trained to process complex sentences involving relative clauses, number agreement, and several types of verb argument structure. Training fails in the case of networks which are fully formed and 'adultlike' in their capacity. Training succeeds only when networks begin with limited working memory and gradually 'mature' to the adult state. This result suggests that rather than being a limitation, developmental restrictions on resources may constitute a necessary prerequisite for mastering certain complex domains. Specifically, successful learning may depend on starting small.