Cogprints

Are feedforward and recurrent networks systematic? Analysis and implications for a connectionist cognitive architecture

Phillips, S. (1998) Are feedforward and recurrent networks systematic? Analysis and implications for a connectionist cognitive architecture. [Journal (Paginated)]

Full text available as:

[img] Postscript
428Kb

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.

Item Type:Journal (Paginated)
Keywords:strong systematicity, connectionism, classicism, feedforward network, recurrent network, tensor network, weight sharing, local representation, compositionality, association, relation
Subjects:Psychology > Cognitive Psychology
Computer Science > Neural Nets
Philosophy > Philosophy of Mind
ID Code:520
Deposited By: Phillips, Steven
Deposited On:10 Dec 1998
Last Modified:11 Mar 2011 08:54

Metadata

Repository Staff Only: item control page