Are Feedforward and Recurrent Networks Systematic? Analysis and Implications for a Connectionist Cognitive Architecture
作者:
Steven Phillips,
期刊:
Connection Science
(Taylor Available online 1998)
卷期:
Volume 10,
issue 2
页码: 137-160
ISSN:0954-0091
年代: 1998
DOI:10.1080/095400998116549
出版商: Taylor & Francis Group
关键词: Systematicity;Architecture;Feedforward;Recurrent
数据来源: Taylor
摘要:
Human cognition is said to be systematic: cognitive ability generalizes to structurally related behaviours. The connectionist approach to cognitive theorizing has been strongly criticized for its failure to explain systematicity. Demonstrations of generalization notwithstanding, I show that two widely used networks (feedforward and recurrent) do not support systematicity under the condition of local input/output representations. For a connectionist explanation of systematicity, these results leave two choices: either (1) develop models capable of systematicity under local input/output representations or (2) justify the choice of similarity-based (non-local) component representations sufficient for systematicity.
点击下载:
PDF (323KB)
返 回