Fodor J
Center for Cognitive Science, Rutgers University, Piscataway, NJ 08855, USA.
Cognition. 1997 Jan;62(1):109-19. doi: 10.1016/s0010-0277(96)00780-9.
Paul Smolensky has recently announced that the problem of explaining the compositionality of concepts within a connectionist framework is solved in principle. Mental representations are vectors over the activity states of connectionist "units", but the vectors encode Classical trees, whose structural properties in turn "acausally" explain the facts of compositionality. This sounds suspiciously like the offer of a free lunch, and it turns out, upon examination, that there is nothing to it.
保罗·斯莫伦斯基最近宣称，在联结主义框架内解释概念的组合性问题原则上已得到解决。心理表征是联结主义“单元”活动状态上的向量，但这些向量编码经典树状结构，其结构属性反过来又“非因果地”解释了组合性的事实。这听起来可疑地像是天上掉馅饼，而经审视后发现，根本不是那么回事。
