This site has been permanently archived. This is a static copy provided by the University of Southampton.

TY - GEN ID - cogprints520 UR - http://cogprints.org/520/ A1 - Phillips, S. Y1 - 1998/// N2 - 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. KW - strong systematicity KW - connectionism KW - classicism KW - feedforward network KW - recurrent network KW - tensor network KW - weight sharing KW - local representation KW - compositionality KW - association KW - relation TI - Are feedforward and recurrent networks systematic? Analysis and implications for a connectionist cognitive architecture SP - 137 AV - public EP - 160 ER -