"520","Are feedforward and recurrent networks systematic? Analysis and implications for a connectionist cognitive architecture","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.","http://cogprints.org/520/","Phillips, S.","UNSPECIFIED","       <span class=\"person_name\">Phillips, S.</span>     (1998)  <a href=\"http://cogprints.org/520/\"><em>Are feedforward and recurrent networks systematic? Analysis and implications for a connectionist cognitive architecture.</em></a>       [Journal (Paginated)]           ","","1998"