Superpositional connectionism: A reply to Marinov

Andy Clark*

*Corresponding author for this work

Research output: Contribution to journalLetterpeer-review

1 Citation (Scopus)


Marinov's critique I argue, is vitiated by its failure to recognize the distinctive role of superposition within the distributed connectionist paradigm. The use of so-called 'subsymbolic' distributed encodings alone is not, I agree, enough to justify treating distributed connectionism as a distinctive approach. It has always been clear that microfeatural decomposition is both possible and actual within the confines of recognizably classical approaches. When such approaches also involve statistically-driven learning algorithms - as in the case of ID3 - the fundamental differences become even harder to spot. To see them, it is necessary to consider not just the nature of an acquired input-output function but the nature of the representational scheme underlying it. Differences between such schemes make themselves best felt outside the domain of immediate problem solving. It is in the more extended contexts of performance DURING learning and cognitive change as a result of SUBSEQUENT training on new tasks (or simultaneous training on several tasks) that the effects of superpositional storage techniques come to the fore. I conclude that subsymbols, distribution and statistically driven learning alone are indeed not of the essence. But connectionism is not just about subsymbols and distribution. It is about the generation of whole subsymbol SYSTEMS in which multiple distributed representations are created and superposed.

Original languageEnglish
Pages (from-to)271-281
Number of pages11
JournalMinds and Machines
Issue number3
Publication statusPublished - Aug 1993
Externally publishedYes


  • Connectionism
  • distribution
  • subsymbol
  • symbol


Dive into the research topics of 'Superpositional connectionism: A reply to Marinov'. Together they form a unique fingerprint.

Cite this