creators_name: Phillips, S. creators_name: Halford, G. S. editors_name: Shafto, M. G. editors_name: Langley, P. type: confpaper datestamp: 1998-12-09 lastmod: 2011-03-11 08:54:16 metadata_visibility: show title: Systematicity: Psychological evidence with connectionist implications ispublished: pub subjects: cog-psy subjects: comp-sci-neural-nets subjects: phil-mind full_text_status: public keywords: systematicity, connectionism, classicism, relational schema, feedforward network, recurrent network, learning transfer, schema induction abstract: At root, the systematicity debate over classical versus connectionist explanations for cognitive architecture turns on quantifying the degree to which human cognition is systematic. We introduce into the debate recent psychological data that provides strong support for the purely structure-based generalizations claimed by Fodor and Pylyshyn (1988). We then show, via simulation, that two widely used connectionist models (feedforward and simple recurrent networks) do not capture the same degree of generalization as human subjects. However, we show that this limitation is overcome by tensor networks that support relational processing. date: 1997 date_type: published publisher: Lawrence Erlbaum Associates, Marwah, New Jersey pagerange: 614-619 refereed: FALSE citation: Phillips, S. and Halford, G. S. (1997) Systematicity: Psychological evidence with connectionist implications. [Conference Paper] document_url: http://cogprints.org/763/2/systempsych.ps