학술논문

Are feedforward and recurrent networks systematic? Analysis and implications for a connectionist cognitive architecture
Document Type
Journal Article
Author
Source
Phillips, S. (1998) Are feedforward and recurrent networks systematic? Analysis and implications for a connectionist cognitive architecture. [Journal (Paginated)]
Subject
Psychology: Cognitive Psychology
Computer Science: Neural Nets
Philosophy: Philosophy of Mind
Cognitive Psychology
Neural Nets
Philosophy of Mind
Language
Abstract
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 (nonlocal) component representations sufficient for systematicity.