Compiled by David Chalmers (Editor) and David Bourget (Assistant Editor), Australian National University. Part of MindPapers. Suggest an entry.

Javascript Menu by Deluxe-Menu.com		All fields Surname Advanced
		click here for help on how to search

Search tips

There are three kinds of search you can perform:

All fields

This mode searches for entries containing all the entered words in their title, author, date, comment field, or in any of many other fields showing on MindPapers pages.

Surname

This mode searches for entries containing the text string you entered in their author field. Note that the database does not have first names for all authors, so it is preferable to search only by surnames. If you search for a full name or a name with an initial, enter it in the format used internally by MindPapers, namely the "Lastname, Firstname" or "Lastname, F." format.

Advanced

This mode differs from the all fields mode in two respects. First, some information not publicly available on MindPapers is searched, e.g., abstracts and excerpts gathered by the MindPapers crawler, which are not always accurate but can help broaden one's search. Second, you may prefix any term with a '+' or '-' to narrow the search to entries containing it or not containing it, respectively. Terms which are not prefixed by a '+' are not mandatory. Instead, they are weighed depending on their frequency in order to determine the best search results. You may also search for a literal string composed of several words by putting them in double quotation marks (").

Note that short and / or common words are ignored by the search engine.

Try MindPapers to find published items which are available on a subscription basis.

close help

Philosophy of artificial intelligence :: Philosophy of connectionism

• Connectionism and compositionality [23]
• Representation in connectionism [20]
• Connectionism and eliminativism [6]
• The connectionist/classical debate [15]
• Subsymbolic computation [6]
• Philosophy of connectionism, misc. [21]
• Philosophy of connectionism, foundational empirical issues [14]

Connectionism and compositionality

See also: Symbols and symbol systems, Representation in connectionism, The connectionist/classical debate, Philosophy of connectionism, misc., Language and thought, The language of thought.

• Kenneth Aizawa (1997). The role of the systematicity argument in classicism and connectionism.   (More)
• Murat Aydede (1997). Language of thought: The connectionist contribution.   (Abstract & more)
  Abstract:   Fodor and Pylyshyn's critique of connectionism has posed a challenge to connectionists: Adequately explain such nomological regularities as systematicity and productivity without postulating a "language of thought" (LOT). Some connectionists like Smolensky took the challenge very seriously, and attempted to meet it by developing models that were supposed to be non-classical. At the core of these attempts lies the claim that connectionist models can provide a representational system with a combinatorial syntax and processes sensitive to syntactic structure. They are not implementation models because, it is claimed, the way they obtain syntax and structure sensitivity is not "concatenative," hence "radically different" from the way classicists handle them. In this paper, I offer an analysis of what it is to physically satisfy/realize a formal system. In this context, I examine the minimal truth-conditions of LOT Hypothesis. From my analysis it will follow that concatenative realization of formal systems is irrelevant to LOTH since the very notion of LOT is indifferent to such an implementation level issue as concatenation. I will conclude that to the extent to which they can explain the law-like cognitive regularities, a certain class of connectionist models proposed as radical alternatives to the classical LOT paradigm will in fact turn out to be LOT models, even though new and potentially very exciting ones
  Additional links for this entry:
  http://web.clas.ufl.edu/users/maydede/lot.connex.pdf
  http://www.ingentaconnect.com/content/klu/mind/1997/00000007/00000001/00115552
  http://www.springerlink.com/content/content/v8365g5vp26x7x75/fulltext.pdf
  http://www.springerlink.com/content/v8365g5vp26x7x75/fulltext.pdf
  http://www.kluweronline.com/article.asp?PIPS=115552&PDF=1
  http://www.springerlink.com/index/V8365G5VP26X7X75.pdf
  
• Keith Butler (1995). Compositionality in cognitive models: The real issue.   (More)
  Additional links for this entry:
  http://www.springerlink.com/content/t05q0506v1349189/fulltext.pdf
  http://www.springerlink.com/index/T05Q0506V1349189.pdf
  
• David Chalmers (1993). Connectionism and compositionality: Why Fodor and Pylyshyn were wrong.   (Abstract & more)
  Abstract: This paper offers both a theoretical and an experimental perspective on the relationship between connectionist and Classical (symbol-processing) models. Firstly, a serious flaw in Fodor and Pylyshyn’s argument against connectionism is pointed out: if, in fact, a part of their argument is valid, then it establishes a conclusion quite different from that which they intend, a conclusion which is demonstrably false. The source of this flaw is traced to an underestimation of the differences between localist and distributed representation. It has been claimed that distributed representations cannot support systematic operations, or that if they can, then they will be mere implementations of traditional ideas. This paper presents experimental evidence against this conclusion: distributed representations can be used to support direct structure-sensitive operations, in a man- ner quite unlike the Classical approach. Finally, it is argued that even if Fodor and Pylyshyn’s argument that connectionist models of compositionality must be mere implementations were correct, then this would still not be a serious argument against connectionism as a theory of mind
• David Chalmers (online). Deep systematicity and connectionist representation.   (Abstract & more)
  Abstract: 1. I think that by emphasizing theoretical spaces of representations, Andy has put his finger on an issue that is key to connectionism's success, and whose investigation will be a key determinant of the field's further progress. I also think that if we look at representational spaces in the right way, we can see that they are deeply related to classical phenomenon of systematicity in representation. I want to argue that the key to understanding representational spaces, and in particular their ability to capture the deep organization underlying various problems, lies in the idea of what I will call
  Additional links for this entry:
  http://consc.net/notes/clark-comments.html
  
• David Chalmers (1990). Syntactic transformations on distributed representations.   (Abstract & more)
  Abstract: There has been much interest in the possibility of connectionist models whose representations can be endowed with compositional structure, and a variety of such models have been proposed. These models typically use distributed representations that arise from the functional composition of constituent parts. Functional composition and decomposition alone, however, yield only an implementation of classical symbolic theories. This paper explores the possibility of moving beyond implementation by exploiting holistic structure-sensitive operations on distributed representations. An experiment is performed using Pollack’s Recursive Auto-Associative Memory. RAAM is used to construct distributed representations of syntactically structured sentences. A feed-forward network is then trained to operate directly on these representations, modeling syn- tactic transformations of the represented sentences. Successful training and generalization is obtained, demonstrating that the implicit structure present in these representations can be used for a kind of structure-sensitive processing unique to the connectionist domain
  Additional links for this entry:
  http://citeseer.ist.psu.edu/517265.html
  http://citeseer.ist.psu.edu/chalmers90syntactic.html
  http://www.u.arizona.edu/~chalmers/papers/transformations.pdf
  http://www.informaworld.com/index/776705615.pdf
  
• M. H. Christiansen & Nick Chater (1994). Generalization and connectionist language learning.   (More)
  Additional links for this entry:
  http://www.blackwell-synergy.com/doi/abs/10.1111/j.1468-0017.1994.tb00226.x
  
• Jerry Fodor & Zenon Pylyshyn (1988). Connectionism and cognitive architecture.   (Abstract & more)
  Abstract: This paper explores the difference between Connectionist proposals for cognitive a r c h i t e c t u r e a n d t h e s o r t s o f m o d e l s t hat have traditionally been assum e d i n c o g n i t i v e s c i e n c e . W e c l a i m t h a t t h e m a j o r d i s t i n c t i o n i s t h a t , w h i l e b o t h Connectionist and Classical architectures postulate representational mental states, the latter but not the former are committed to a symbol-level of representation, or to a ‘language of thought’: i.e., to representational states that have combinatorial syntactic and semantic structure. Several arguments for combinatorial structure in mental representations are then reviewed. These include arguments based on the ‘systematicity’ of mental representation: i.e., on the fact that cognitive capacities always exhibit certain symmetries, so that the ability to entertain a given thought implies the ability to entertain thoughts with semantically related contents. We claim that such arguments make a powerful case that mind/brain architecture is not Connectionist at the cognitive level. We then consider the possibility that Connectionism may provide an account of the neural (or ‘abstract neurological’) structures in which Classical cognitive architecture is implemented. We survey a n u m b e r o f t h e s t a n d a r d a r g u m e n t s t h a t h a v e b e e n o f f e r e d i n f a v o r o f Connectionism, and conclude that they are coherent only on this interpretation
  Additional links for this entry:
  http://portal.acm.org/citation.cfm?id=58067
  http://www.blutner.de/philom/connect/jaf.pdf
  http://ruccs.rutgers.edu/ftp/pub/papers/jaf.pdf
  http://portal.acm.org/citation.cfm?id=190704.190740
  http://www.ii.metu.edu.tr/~tekman/fodor&pylyshyn.pdf
  http://citeseer.ist.psu.edu/fodor88connectionism.html
  http://watarts.uwaterloo.ca/~celiasmi/courses/Phil256/papers/fodor.pylyshyn.1988.Connectionism cog architec.bbs.pdf
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bKr8GASZ&sig=lvbjst___yAcJlOgVzyRdzEV09k
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bIt7BHPT&sig=W9wLTgrsP59cPqZhSN0ysQbSVoM
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bHr6CFR-&sig=ic0bVVM1PfuvCnadV8OCRGBbNA4
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bGv5HHV-&sig=UkXTSX19hHzvmMUKvLT-lq0r50I
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z7kKubBBQY&sig=HFGXyuxr_1mxH5ACFOe-zyaTw4o
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bLzaEEXV&sig=e9QEFe5nD4bGAK5W4dDIRZBKNuM
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bIz7HCQU&sig=4TMgHlnpnDyehNFJT-NG470Bbz8
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bMvaHGVW&sig=9UEpXL5XYxZdQa3NvX7yU9iikyw
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bKx9AJPT&sig=7sjHbKdagqCd6sUT-Kk-fcITZlc
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bHx6HEPT&sig=9ypKOA18BrlaitMu_it-TVCBfUw
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z7kKr7GFP0&sig=tdUqyz4ARusp_kokrKNOJedNknk
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bLtaAHPT&sig=cUrJjY2sKfVLW5Zp1ZtlEsdhcaM
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z8bJv8BJW0&sig=Qe8qR4Go6tnV95LlvTT6ELC_0Ds
  http://books.google.com/books?hl=en&lr=&id=vZ1t2AnZy3UC&oi=fnd&pg=PA3&ots=Z7kKwbCBVX&sig=iCTIyYq8EOvBdYu-srEXgyt-HoM
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O2dHfvmUIJ&sig=7hnYM8j4zdtpN4THjVSpzpGFEDs
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34InykTQC&sig=F0CONzdT49KnmoIp41iOngjBa_A
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34IhygWIA&sig=Zks6FRmma9XZGHW2EO1kvwIxesQ
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34DjtnWOI&sig=ohgYrPGd2Ut0_gQqvfJPXg0_xJo
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34FnvnRJB&sig=snID_Ptc5j-K-DxZvSjAScHkD6s
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34GjwhYPJ&sig=YnoEHTZY6rwzlL8DcfCj45uUQo0
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34JjynVOD&sig=XBIWzRchQULcgPTlX6HyBgOg_pQ
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34HfwmPLG&sig=35GDmDcPG526574Ar-pZaGlfYXA
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34ElunTIA&sig=OzlrEEZ2Td9CGt5mgUD99UXGCWE
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34HlxgYIA&sig=ZsqjFV8LrCGXI-3jf8Pliu_sVsc
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34FhvhWIA&sig=1yq1WHwwotr3qVSaqN0K4StIWc8
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O34EfuiUKI&sig=lDwkN-dMTxlLX_1XELpsD4ONtM4
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O2dHizhQJF&sig=s7d-fmzg598bYH-IpAMNrcyO8eo
  http://books.google.com/books?hl=en&lr=&id=ZLIAbDZzJ5sC&oi=fnd&pg=PA90&ots=O2dHkziQOE&sig=6AJnryXo_R8vj8qseWkK5DD31zQ
  http://www.phil.canterbury.ac.nz/tom_bestor/e-texts/Fodor and Pylyshyn - Connectionism and Cognitive Architecture (1988).pdf
  http://citeseer.comp.nus.edu.sg/cache/papers/cs/22408/http:zSzzSzruccs.rutgers.eduzSzpubzSzpaperszSzjaf.pdf/fodor88connectionism.pdf
  http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=2450716&dopt=Citation
  
• Robert Hadley (1997). Cognition, systematicity, and nomic necessity.   (More)
  Additional links for this entry:
  http://www.ingentaconnect.com/content/bpl/mila/1997/00000012/00000002/art00002
  http://www.ingentaconnect.com/content/bpl/mila/1997/00000012/00000002/art00040
  http://www.blackwell-synergy.com/doi/abs/10.1111/j.1468-0017.1997.tb00066.x
  http://www.blackwell-synergy.com/links/doi/10.1111/1468-0017.00040
  http://www.blackwell-synergy.com/doi/abs/10.1111/1468-0017.00040
  
• Robert Hadley (1997). Explaining systematicity: A reply to Kenneth Aizawa.   (Abstract & more)
  Abstract:   In his discussion of results which I (with Michael Hayward) recently reported in this journal, Kenneth Aizawa takes issue with two of our conclusions, which are: (a) that our connectionist model provides a basis for explaining systematicity within the realm of sentence comprehension, and subject to a limited range of syntax (b) that the model does not employ structure-sensitive processing, and that this is clearly true in the early stages of the network''s training. Ultimately, Aizawa rejects both (a) and (b) for reasons which I think are ill-founded. In what follows, I offer a defense of our position. In particular, I argue (1) that Aizawa adopts a standard of explanation that many accepted scientific explanations could not meet, and (2) that Aizawa misconstrues the relevant meaning of structure-sensitive process
  Additional links for this entry:
  http://www.csa.com/partners/viewrecord.php?requester=gs&collection=TRD&recid=316242CI
  http://www.ingentaconnect.com/content/klu/mind/1997/00000007/00000004/00122810
  http://www.springerlink.com/content/m395128140134l86/fulltext.pdf
  http://www.kluweronline.com/article.asp?PIPS=122810&PDF=1
  http://www.springerlink.com/index/M395128140134L86.pdf
  
• Robert Hadley (1994). Systematicity in connectionist language learning.   (More)
  Additional links for this entry:
  http://www.blackwell-synergy.com/doi/abs/10.1111/j.1468-0017.1994.tb00225.x
  
• Robert Hadley & M. B. Hayward (1997). Strong semantic systematicity from Hebbian connectionist learning.   (Abstract & more)
  Abstract:   Fodor's and Pylyshyn's stand on systematicity in thought and language has been debated and criticized. Van Gelder and Niklasson, among others, have argued that Fodor and Pylyshyn offer no precise definition of systematicity. However, our concern here is with a learning based formulation of that concept. In particular, Hadley has proposed that a network exhibits strong semantic systematicity when, as a result of training, it can assign appropriate meaning representations to novel sentences (both simple and embedded) which contain words in syntactic positions they did not occupy during training. The experience of researchers indicates that strong systematicity in any form is difficult to achieve in connectionist systems.Herein we describe a network which displays strong semantic systematicity in response to Hebbian, connectionist training. During training, two-thirds of all nouns are presented only in a single syntactic position (either as grammatical subject or object). Yet, during testing, the network correctly interprets thousands of sentences containing those nouns in novel positions. In addition, the network generalizes to novel levels of embedding. Successful training requires a, corpus of about 1000 sentences, and network training is quite rapid. The architecture and learning algorithms are purely connectionist, but classical insights are discernible in one respect, viz, that complex semantic representations spatially contain their semantic constituents. However, in other important respects, the architecture is distinctly non-classical
  Additional links for this entry:
  http://portal.acm.org/citation.cfm?id=596704.596727
  http://www.ingentaconnect.com/content/klu/mind/1997/00000007/00000001/00112501
  http://www.springerlink.com/content/k4l352163l5777l2/fulltext.pdf
  http://www.springerlink.com/index/K4L352163L5777L2.pdf
  
• W. F. G. Haselager & J. F. H. Van Rappard (1998). Connectionism, systematicity, and the frame problem.   (Abstract & more)
  Abstract:   This paper investigates connectionism's potential to solve the frame problem. The frame problem arises in the context of modelling the human ability to see the relevant consequences of events in a situation. It has been claimed to be unsolvable for classical cognitive science, but easily manageable for connectionism. We will focus on a representational approach to the frame problem which advocates the use of intrinsic representations. We argue that although connectionism's distributed representations may look promising from this perspective, doubts can be raised about the potential of distributed representations to allow large amounts of complexly structured information to be adequately encoded and processed. It is questionable whether connectionist models that are claimed to effectively represent structured information can be scaled up to a realistic extent. We conclude that the frame problem provides a difficulty to connectionism that is no less serious than the obstacle it constitutes for classical cognitive science
  Additional links for this entry:
  http://www.csa.com/partners/viewrecord.php?requester=gs&collection=TRD&recid=371129CI
  http://www.ingentaconnect.com/content/klu/mind/1998/00000008/00000002/00150466
  http://www.springerlink.com/content/um0x474450532866/fulltext.pdf
  http://www.kluweronline.com/article.asp?PIPS=150466&PDF=1
  http://www.springerlink.com/index/UM0X474450532866.pdf
  
• L. F. Niklasson & Tim van Gelder (1994). On being systematically connectionist.   (Abstract & more)
  Abstract: In 1988 Fodor and Pylyshyn issued a challenge to the newly-popular connectionism: explain the systematicity of cognition without merely implementing a so-called classical architecture. Since that time quite a number of connectionist models have been put forward, either by their designers or by others, as in some measure demonstrating that the challenge can be met (e.g., Pollack, 1988, 1990; Smolensky, 1990; Chalmers, 1990; Niklasson and Sharkey, 1992; Brousse, 1993). Unfortu- nately, it has generally been unclear whether these models actually do have this implication (see, for instance, the extensive philosophical debate in Smolensky, 1988; Fodor and McLaughlin, 1990; van Gelder, 1990, 1991; McLaughlin, 1993a, 1993b; Clark, 1993). Indeed, we know of no major supporter of classical orthodoxy who has felt compelled, by connectionist models and argu- ments, to concede in print that connectionists have in fact delivered a non-classical explanation of systematicity
  Additional links for this entry:
  http://citeseer.ist.psu.edu/niklasson94being.html
  http://www.his.se/ida/~lars/PUBLICATIONS/m_and_l.ps
  http://www.arts.unimelb.edu.au/~tgelder/papers/m_and_l.pdf
  http://www.philosophy.unimelb.edu.au/tgelder/papers/m_and_l.pdf
  http://www.phil.canterbury.ac.nz/tom_bestor/e-texts/Niklasson and van Gelder - On being systematically connectionist 1994.ps
  http://www.blackwell-synergy.com/doi/abs/10.1111/j.1468-0017.1994.tb00227.x
  
• Steven Petersen & Adina Roskies (2001). Visualizing human brain function.   (Abstract & more)
  Abstract: Running head: Functional neuroimaging Abstract Several recently developed techniques enable the investigation of the neural basis of cognitive function in the human brain. Two of these, PET and fMRI, yield whole-brain images reflecting regional neural activity associated with the performance of specific tasks. This article explores the spatial and temporal capabilities and limitations of these techniques, and discusses technical, biological, and cognitive issues relevant to understanding the goals and methods of neuroimaging studies. The types of advances in understanding cognitive and brain function made possible with these methods are illustrated with examples from the neuroimaging literature
  Additional links for this entry:
  http://www.dartmouth.edu/~adinar/publications/VisualizingHumanBrainFunct.doc
  
• Stephen Phillips (2002). Does classicism explain universality?   (Abstract & more)
  Abstract:   One of the hallmarks of human cognition is the capacity to generalize over arbitrary constituents. Recently, Marcus (1998, 1998a, b; Cognition 66, p. 153; Cognitive Psychology 37, p. 243) argued that this capacity, called universal generalization (universality), is not supported by Connectionist models. Instead, universality is best explained by Classical symbol systems, with Connectionism as its implementation. Here it is argued that universality is also a problem for Classicism in that the syntax-sensitive rules that are supposed to provide causal explanations of mental processes are either too strict, precluding possible generalizations; or too lax, providing no information as to the appropriate alternative. Consequently, universality is not explained by a Classical theory
  Additional links for this entry:
  http://www.springerlink.com/content/9lycmrkn91j71qqe/fulltext.pdf
  http://www.kluweronline.com/article.asp?PIPS=408595&PDF=1
  http://www.springerlink.com/index/9LYCMRKN91J71QQE.pdf
  
• Jordan Pollack (1990). Recursive distributed representations.   (More)
  Additional links for this entry:
  http://demo.cs.brandeis.edu/papers/raam.pdf
  http://portal.acm.org/citation.cfm?id=102423
  http://helen.cs-i.brandeis.edu/papers/raam.pdf
  http://www.ing.unisi.it/~monica/Paper/p19.ps.gz
  http://www.uow.edu.au/~markus/apods/doc/papers/raam.ps
  http://www.blutner.de/philom/connect/pollack90recursive.pdf
  http://www.blutner.de/NeuralNets/Texts/pollack90recursive.pdf
  http://www.idi.ntnu.no/emner/it3708/archive/2004/files/raam.pdf
  http://ftp.uni-koeln.de/neural-nets/papers/pollack.newraam.ps.gz
  http://www.cse.ohio-state.edu/~jj/pub/papers/89-JP-RECURSIVE.ps.Z
  http://www.umiacs.umd.edu/~ymarton/ling849/pollack90recursive.pdf
  http://ftp.funet.fi/pub/sci/neural/neuroprose/pollack.newraam.ps.Z
  http://www.funet.fi/pub/sci/neural/neuroprose/pollack.newraam.ps.Z
  http://amor.rz.hu-berlin.de/~h0998dgh/philom/connect/pollack90recursive.pdf
  http://amor.rz.hu-berlin.de/~h0998dgh/NeuralNets/Texts/pollack90recursive.pdf
  http://www.ftp.funet.fi/ftp/pub/sci/ai/neural/neuroprose/pollack.newraam.ps.Z
  http://www.csa.com/partners/viewrecord.php?requester=gs&collection=TRD&recid=2470980CI
  
• Jurgen Schroder (1998). Knowledge of rules, causal systematicity, and the language of thought.   (Abstract & more)
  Abstract:   Martin Davies' criterion for the knowledge of implicit rules, viz. the causal systematicity of cognitive processes, is first exposed. Then the inference from causal systematicity of a process to syntactic properties of the input states is examined. It is argued that Davies' notion of a syntactic property is too weak to bear the conclusion that causal systematicity implies a language of thought as far as the input states are concerned. Next, it is shown that Davies' criterion leads to a counterintuitive consequence: it groups together distributed connectionist systems with look-up tables. To avoid this consequence, a modified construal of causal systematicity is proposed and Davies' argument for the causal systematicity of thought is shown to be question-begging. It is briefly sketched how the modified construal links up with multiple dispositions of the same categorical base. Finally, the question of the causal efficacy of single rules is distinguished from the question of their psychological reality: implicit rules might be psychologically real without being causally efficacious
  Additional links for this entry:
  http://www.ingentaconnect.com/content/klu/synt/1998/00000117/00000003/00188458
  http://www.springerlink.com/content/w8735t5747313v32/fulltext.pdf
  http://www.kluweronline.com/article.asp?PIPS=188458&PDF=1
  http://www.springerlink.com/index/W8735T5747313V32.pdf
  
• Paul Smolensky (1990). Tensor product variable binding and the representation of symbolic structures in connectionist systems.   (More)
  Additional links for this entry:
  http://www.csa.com/partners/viewrecord.php?requester=gs&collection=TRD&recid=2470919CI
  
• Tim van Gelder (1990). Compositionality: A connectionist variation on a classical theme.   (More)
  Additional links for this entry:
  http://www.leaonline.com/doi/pdfplus/10.1207/s15516709cog1403_2
  http://www.cogsci.rpi.edu/CSJarchive/1990v14/i03/p0355p0384/MAIN.PDF
  
• Tim van Gelder (online). Can connectionist models exhibit non-classical structure sensitivity?   (Abstract & more)
  Abstract: Department of Computer Science Philosophy Program, Research School of Social Sciences University of Skövde, S-54128, SWEDEN Australian National University, Canberra ACT 0200
  Additional links for this entry:
  http://citeseer.ist.psu.edu/niklasson94can.html
  http://www.arts.unimelb.edu.au/~tgelder/papers/cogs94.pdf
  http://www.philosophy.unimelb.edu.au/tgelder/papers/cogs94.pdf
  http://www.phil.canterbury.ac.nz/tom_bestor/e-texts/iklasson and van Gelder - connectionist structure sensitivity.pdf
  http://www.phil.canterbury.ac.nz/tom_bestor/e-texts/Niklassen and van Gelder - Can connectionist models exhibit non-classical structure sensitivity.pdf
  
• Tim van Gelder (1994). On being systematically connectionist.   (Abstract & more)
  Abstract: In 1988 Fodor and Pylyshyn issued a challenge to the newly-popular connectionism: explain the systematicity of cognition without merely implementing a so-called classical architecture. Since that time quite a number of connectionist models have been put forward, either by their designers or by others, as in some measure demonstrating that the challenge can be met (e.g., Pollack, 1988, 1990; Smolensky, 1990; Chalmers, 1990; Niklasson and Sharkey, 1992; Brousse, 1993). Unfortu- nately, it has generally been unclear whether these models actually do have this implication (see, for instance, the extensive philosophical debate in Smolensky, 1988; Fodor and McLaughlin, 1990; van Gelder, 1990, 1991; McLaughlin, 1993a, 1993b; Clark, 1993). Indeed, we know of no major supporter of classical orthodoxy who has felt compelled, by connectionist models and argu- ments, to concede in print that connectionists have in fact delivered a non-classical explanation of systematicity
  Additional links for this entry:
  http://citeseer.ist.psu.edu/niklasson94being.html
  http://www.his.se/ida/~lars/PUBLICATIONS/m_and_l.ps
  http://www.arts.unimelb.edu.au/~tgelder/papers/m_and_l.pdf
  http://www.philosophy.unimelb.edu.au/tgelder/papers/m_and_l.pdf
  http://www.phil.canterbury.ac.nz/tom_bestor/e-texts/Niklasson and van Gelder - On being systematically connectionist 1994.ps
  
• Jonathan Waskan & William Bechtel (1997). Directions in connectionist research: Tractable computations without syntactically structured representations.   (Abstract & more)
  Abstract: Figure 1: A pr ototyp ical exa mple of a three-layer feed forward network, used by Plunkett and M archm an (1 991 ) to simulate learning the past-tense of En glish verbs. The inpu t units encode representations of the three phonemes of the present tense of the artificial words used in this simulation. Th e netwo rk is trained to produce a representation of the phonemes employed in the past tense form and the suffix (/d/, /ed/, or /t/) used on regular verbs. To run the network, each input unit is assigned an activation value o f 0 or 1 , dep ending on whethe r the featu re is present or not. Eac h input unit is conne cted to each of the 30 hidden units by a we ighted conn ection and p rovid es an inp ut to each hidden unit equal to the product of the input unit's activation and the weight. Each hidd en unit's activation is then determined by summing ov er the va lues co ming fro m each inp ut unit to deter mine a netinput, and then applying a non-linear function (e.g., the logistic function 1/(1+e^netinput). Th is whole proced ure is
  Additional links for this entry:
  https://netfiles.uiuc.edu/waskan/www/Waskan and Bechtel.pdf
  http://www.ingentaconnect.com/content/bpl/meta/1997/00000028/F0020001/art00002
  http://www.ingentaconnect.com/content/bpl/meta/1997/00000028/f0020001
  http://www.blackwell-synergy.com/links/doi/10.1111/1467-9973.00040
  http://www.blackwell-synergy.com/doi/abs/10.1111/1467-9973.00040
  

Representation in connectionism

See also: Computation and representation, Connectionism and compositionality, The connectionist/classical debate, Subsymbolic computation, Philosophy of connectionism, misc., Representation.

• William Bechtel (1994). Natural deduction in connectionist systems.   (Abstract & more)
  Abstract:   The relation between logic and thought has long been controversial, but has recently influenced theorizing about the nature of mental processes in cognitive science. One prominent tradition argues that to explain the systematicity of thought we must posit syntactically structured representations inside the cognitive system which can be operated upon by structure sensitive rules similar to those employed in systems of natural deduction. I have argued elsewhere that the systematicity of human thought might better be explained as resulting from the fact that we have learned natural languages which are themselves syntactically structured. According to this view, symbols of natural language are external to the cognitive processing system and what the cognitive system must learn to do is produce and comprehend such symbols. In this paper I pursue that idea by arguing that ability in natural deduction itself may rely on pattern recognition abilities that enable us to operate on external symbols rather than encodings of rules that might be applied to internal representations. To support this suggestion, I present a series of experiments with connectionist networks that have been trained to construct simple natural deductions in sentential logic. These networks not only succeed in reconstructing the derivations on which they have been trained, but in constructing new derivations that are only similar to the ones on which they have been trained
  Additional links for this entry:
  http://citeseer.ist.psu.edu/bechtel94natural.html
  http://www.blutner.de/NeuralNets/Texts/DERIVATI.pdf
  http://mechanism.ucsd.edu/~bill/research/DERIVATI.pdf
  http://amor.rz.hu-berlin.de/~h0998dgh/NeuralNets/Texts/DERIVATI.pdf
  http://amor.cms.hu-berlin.de/~h0998dgh/NeuralNets/Texts/DERIVATI.pdf
  http://www.springerlink.com/content/q71158t2342jl517/fulltext.pdf
  http://www.springerlink.com/index/Q71158T2342JL517.pdf
  
• Keith Butler (1995). Representation and computation in a deflationary assessment of connectionist cognitive science.   (Abstract & more)
  Abstract:   Connectionism provides hope for unifying work in neuroscience, computer science, and cognitive psychology. This promise has met with some resistance from Classical Computionalists, which may have inspired Connectionists to retaliate with bold, inflationary claims on behalf of Connectionist models. This paper demonstrates, by examining three intimately connected issues, that these inflationary claims made on behalf of Connectionism are wrong. This should not be construed as an attack on Connectionism, however, since the inflated claims made on its behalf have the look of cures for which there are no ailments. There is nothing wrong with Connectionism for its failure to solve illusory problems
  Additional links for this entry:
  http://www.springerlink.com/content/r347125074346147/fulltext.pdf
  http://www.springerlink.com/index/R347125074346147.pdf
  
• Andy Clark (ms). Connectionism, nonconceptual content, and representational redescription.   (More)
• Robert Cummins (1991). The role of representation in connectionist explanation of cognitive capacities.   (More)
• Adrian Cussins (1990). The connectionist construction of concepts.   (Abstract & more)
  Abstract: The character of computational modelling of cognition depends on an underlying theory of representation. Classical cognitive science has exploited the syntax/semantics theory of representation that derives from logic. But this has had the consequence that the kind of psychological explanation supported by classical cognitive science is

  _conceptualist_:

  psychological phenomena are modelled in terms of relations that hold between concepts, and between the sensors/effectors and concepts. This kind of explanation is inappropriate for the Proper Treatment of Connectionism (Smolensky 1988)
  Additional links for this entry:
  http://www.haecceia.com/FILES/c3_kings_london.htm
  
• Chris Eliasmith (online). Structure without symbols: Providing a distributed account of high-level cognition.   (Abstract & more)
  Abstract: There has been a long-standing debate between symbolicists and connectionists concerning the nature of representation used by human cognizers. In general, symbolicist commitments have allowed them to provide superior models of high-level cognitive function. In contrast, connectionist distributed representations are preferred for providing a description of low-level cognition. The development of Holographic Reduced Representations (HRRs) has opened the possibility of one representational medium unifying both low-level and high-level descriptions of cognition. This paper describes the relative strengths and weaknesses of symbolic and distributed representations. HRRs are shown to capture the important strengths of both types of representation. These properties of HRRs allow a rebuttal of Fodor and McLaughlin's (1990) criticism that distributed representations are not adequately structure sensitive to provide a full account of human cognition
• Robert Hadley (2004). On the proper treatment of semantic systematicity.   (Abstract & more)
  Abstract:   The past decade has witnessed the emergence of a novel stance on semantic representation, and its relationship to context sensitivity. Connectionist-minded philosophers, including Clark and van Gelder, have espoused the merits of viewing hidden-layer, context-sensitive representations as possessing semantic content, where this content is partially revealed via the representations'' position in vector space. In recent work, Bodén and Niklasson have incorporated a variant of this view of semantics within their conception of semantic systematicity. Moreover, Bodén and Niklasson contend that they have produced experimental results which not only satisfy a kind of context-based, semantic systematicity, but which, to the degree that reality permits, effectively deals with challenges posed by Fodor and Pylyshyn (1988), and Hadley (1994a). The latter challenge involved well-defined criteria for strong semantic systematicity. This paper examines the relevant claims and experiments of Bodén and Niklasson. It is argued that their case fatally involves two fallacies of equivocation; one concerning ''semantic content'' and the other concerning ''novel test sentences''. In addition, it is argued that their ultimate construal of context sensitive semantics contains serious confusions. These confusions are also found in certain publications dealing with "latent semantic analysis". Thus, criticisms presented here have relevance beyond the work of Bodén and Niklasson
  Additional links for this entry:
  http://portal.acm.org/citation.cfm?id=976702.976735
  http://www.ingentaconnect.com/content/klu/mind/2004/00000014/00000002/05142070
  http://www.springerlink.com/content/p4312417q27100p0/fulltext.pdf
  http://www.kluweronline.com/article.asp?PIPS=5142070&PDF=1
  http://www.springerlink.com/index/P4312417Q27100P0.pdf
  
• W. F. G. Haselager (1999). On the potential of non-classical constituency.   (More)
  Additional links for this entry:
  http://www.nici.kun.nl/~haselag/publications/1999c.pdf
  http://www.socsci.kun.nl/~haselag/publications/1999c.pdf
  http://www.nici.ru.nl/~haselag/publications/NonClassConst99.pdf
  http://www.nici.kun.nl/~haselag/publications/NonClassConst99.pdf
  http://www.socsci.kun.nl/~haselag/publications/NonClassConst99.pdf
  
• Daniel Haybron (2000). The causal and explanatory role of information stored in connectionist networks.   (Abstract & more)
  Abstract:   In this paper I defend the propriety of explaining the behavior of distributed connectionist networks by appeal to selected data stored therein. In particular, I argue that if there is a problem with such explanations, it is a consequence of the fact that information storage in networks is superpositional, and not because it is distributed. I then develop a ``proto-account'''' of causation for networks, based on an account of Andy Clark''s, that shows even superpositionality does not undermine information-based explanation. Finally, I argue that the resulting explanations are genuinely informative and not vacuous
  Additional links for this entry:
  http://www.slu.edu/~haybrond/Connectionist information storage.pdf
  http://www.slu.edu/users/users/haybrond/Connectionist information storage.pdf
  http://www.slu.edu/users/users/haybrond/Connectionist information storage.pdf
  http://www.csa.com/partners/viewrecord.php?requester=gs&collection=TRD&recid=536479CI
  http://www.ingentaconnect.com/content/klu/mind/2000/00000010/00000003/00258827
  http://www.springerlink.com/content/content/t061056966k44051/fulltext.pdf
  http://www.springerlink.com/content/t061056966k44051/fulltext.pdf
  http://www.kluweronline.com/article.asp?PIPS=258827&PDF=1
  http://www.springerlink.com/index/T061056966K44051.pdf
  
• Aarre Laakso & Garrison Cottrell (2000). Content and cluster analysis: Assessing representational similarity in neural systems.   (Abstract & more)
  Abstract: If connectionism is to be an adequate theory of mind, we must have a theory of representation for neural networks that allows for individual differences in weighting and architecture while preserving sameness, or at least similarity, of content. In this paper we propose a procedure for measuring sameness of content of neural representations. We argue that the correct way to compare neural representations is through analysis of the distances between neural activations, and we present a method for doing so. We then use the technique to demonstrate empirically that different artificial neural networks trained by backpropagation on the same categorization task, even with different representational encodings of the input patterns and different numbers of hidden units, reach states in which representations at the hidden units are similar. We discuss how this work provides a rebuttal to Fodor and Lepore's critique of Paul Churchland's state space semantics
  Additional links for this entry:
  http://www.laakshmi.com/aarre/cv/phipsy.pdf
  http://www.cs.ucsd.edu/groups/guru/docs/laakso2000.pdf
  http://www-cse.ucsd.edu/groups/guru/docs/laakso2000.pdf
  http://www.cse.ucsd.edu/groups/guru/docs/laakso2000.pdf
  http://www.informaworld.com/smpp/./ftinterface~content=a713690421~fulltext=713240930
  http://www.ingentaconnect.com/content/routledg/cphp/2000/00000013/00000001/art00002
  http://taylorandfrancis.metapress.com/index/RY0JBTH3PY9B6GF2.pdf
  http://www.informaworld.com/index/RY0JBTH3PY9B6GF2.pdf
  
• Eric Lormand (ms).