CONNECTIONISM AND THE PROBLEM OF SYSTEMATICITY (CONTINUED) - WHY SMOLENSKY SOLUTION STILL DOESNT WORK

Authors
Citation
J. Fodor, CONNECTIONISM AND THE PROBLEM OF SYSTEMATICITY (CONTINUED) - WHY SMOLENSKY SOLUTION STILL DOESNT WORK, Cognition, 62(1), 1997, pp. 109-119
Citations number
6
Categorie Soggetti
Psychology, Experimental
Journal title
ISSN journal
00100277
Volume
62
Issue
1
Year of publication
1997
Pages
109 - 119
Database
ISI
SICI code
0010-0277(1997)62:1<109:CATPOS>2.0.ZU;2-O
Abstract
Paul Smolensky has recently announced that the problem of explaining t he compositionality of concepts within a connectionist framework is so lved in principle. Mental representations are vectors over the activit y states of connectionist ''units'', but the vectors encode Classical trees, whose structural properties in turn ''acausally'' explain the f acts of compositionality. This sounds suspiciously like the offer of a free lunch, and it turns out, upon examination, that there is nothing to it.