Recovery of Unrehearsed Items in Connectionist Models
作者:
PAUL W. B ATKINS,
JAAP M. J MURRE,
期刊:
Connection Science
(Taylor Available online 1998)
卷期:
Volume 10,
issue 2
页码: 99-119
ISSN:0954-0091
年代: 1998
DOI:10.1080/095400998116521
出版商: Taylor & Francis Group
关键词: Gradient-descent Models;Relearning;Memory;Backpropagation
数据来源: Taylor
摘要:
When gradient-descent models with hidden units are retrained on a portion of a previously learned set of items, performance on both the relearned and unrelearned items improves. Previous explanations of this phenomenon have not adequately distinguished recovery, which is dependent on original learning, from generalization, which is independent of original learning. Using a measure of vector similarity to track global changes in the weight state of three-layer networks, we show that (a) unlike in networks without hidden units, recovery occurs in the absence of generalization in networks with hidden units, and (b) when the conditions of learning are varied, changes in the extent of recovery are reflected in changes in the extent to which the weights move back towards their values held after original learning. The implications of this work for rehabilitation studies, human relearning and models of human long-term memory are also considered.
点击下载:
PDF (504KB)
返 回