Notes
- I’ve read this while out walking Bertie the dog. It needs closer study!
- For, Mark Rowlands, see Wikipedia: Mark Rowlands and Mark Rowlands - CV.
- For Jerry Fodor, see Wikipedia: Jerry Fodor.
- For Zenon Pylyshyn, see (the rather feeble) Wikipedia: Zenon Pylyshyn.
- Both Fodor and Pylyshyn were alive and in their prime when this paper was written, so had the option to respond. I don’t – currently – think they did as I couldn’t find anything by fairly diligent Googling!
- For the LOT Hypothesis1, see (as a starter) Wikipedia: Language of thought hypothesis.
- Rowlands quotes various Papers and Books in my possession2:-
→ "Bechtel (William) & Abrahamsen (Adele) - Connectionism & the Mind: Parallel Processing, Dynamics and Evolution in Networks"
→ "Clark (Andy) - Microcognition – Philosophy Cognitive Science & Parallel Distributed Processing"
→ "Field (Hartry) - Mental Representation"
→ "Fodor (Jerry) - Propositional Attitudes"
→ "Fodor (Jerry) - Psychosemantics", Note3
→ "Fodor (Jerry) & Pylyshyn (Zenon) - Connectionism and Cognitive Architecture: A Critical Analysis"
→ "Rumelhart (David), McClelland (James), Etc - Parallel Distributed Processing, Vol 1"
→ "Smolensky (Paul) - On the Proper Treatment of Connectionism"
→ "Touretzky (David S.) & Hinton (Geoffrey E.) - A Distributed Connectionist Production System"
- See also:-
→ "Fodor (Jerry) & McLaughlin (Brian) - Connectionism and the Problem of Systematicity: Why Smolensky's Solution Doesn't Work"
→ "Stich (Stephen) & Warfield (Ted) - Reply to Clark and Smolensky: Do Connectionist Minds Have Beliefs?"
- Most of these are too long and technical to follow up. I suspect they are mostly of historical interest as the field of AI has moved on considerably since they were written.
Author’s Abstract
- In an influential critique, Jerry Fodor and Zenon Pylyshyn point to the existence of a potentially devastating dilemma for connectionism (Fodor and Pylyshyn 19884). Either connectionist models consist in mere associations of unstructured representations, or they consist in processes involving complex representations. If the former, connectionism is mere associationism, and will not be capable of accounting for very much of cognition. If the latter, then connectionist models concern only the implementation of cognitive processes, and are, therefore, not informative at the level of cognition.
- I shall argue that Fodor and Pylyshyn's argument is based on a crucial misunderstanding, the same misunderstanding which motivates the entire language of thought hypothesis.
Contents
- Fodor and Pylyshyn on Connectionism
- Language of Thought Hypotheses
- Motivation for SLT5
- Fodor and Pylyshyn's Case Against Connectionism
- Some Consequences
Comment:
In-Page Footnotes
Footnote 2:
- Or that I could easily acquire. There are other books and papers cited that are either unavailable on-line, or which are far too expensive.
- An exception was "Clark (Andy) - Microcognition – Philosophy Cognitive Science & Parallel Distributed Processing", which ought to have been too expensive, but which I got second-hand for an absolute snip (£3.80 including postage). It also looks really interesting, is made use of a lot in this paper, and is by an author I’ve been ‘following’.
Footnote 3:
- "Fodor (Jerry) - Psychosemantics": I’ve written up the first Chapter – "Fodor (Jerry) - The Persistence of the Attitudes" – of this book which needs converting to Note format.
- This was done while I was an undergraduate at Birkbeck back in 2003. I imagine that I’ve reconstructed time spent (as I didn’t have the leisure to keep timesheets in those days as I was still working full-time) and assumed I’d read the whole book, which I may not have, especially as the 14.25 hours is supposed to include the time spent writing up the first Chapter.
- The whole books needs (another) read in any case.
Footnote 4: Footnote 5:
- Strong Language Of Thought Hypothesis (SLT): Cognitively relevant internal states are states that have semantic content, where this content is identified by way of a sentence, and the structure of any given internal state m mirrors the structure of the proposition p which is expressed by m's content-identifying sentence.
Text Colour Conventions (see disclaimer)
- Blue: Text by me; © Theo Todman, 2025
- Mauve: Text by correspondent(s) or other author(s); © the author(s)