26 found
Order:
  1. On the Proper Treatment of Connectionism.Paul Smolensky - 1988 - Behavioral and Brain Sciences 11 (1):1-23.
    A set of hypotheses is formulated for a connectionist approach to cognitive modeling. These hypotheses are shown to be incompatible with the hypotheses underlying traditional cognitive models. The connectionist models considered are massively parallel numerical computational systems that are a kind of continuous dynamical system. The numerical variables in the system correspond semantically to fine-grained features below the level of the concepts consciously used to describe the task domain. The level of analysis is intermediate between those of symbolic cognitive models (...)
    Direct download (6 more)  
     
    Export citation  
     
    Bookmark   659 citations  
  2. The Constituent Structure of Connectionist Mental States: A Reply to Fodor and Pylyshyn.Paul Smolensky - 1988 - Southern Journal of Philosophy 26 (S1):137-161.
  3.  67
    Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems.Paul Smolensky - 1990 - Artificial Intelligence 46 (1-2):159-216.
  4.  21
    Learning Biases Predict a Word Order Universal.Jennifer Culbertson, Paul Smolensky & Géraldine Legendre - 2012 - Cognition 122 (3):306-329.
    No categories
    Direct download (4 more)  
     
    Export citation  
     
    Bookmark   33 citations  
  5. Cognitive Biases, Linguistic Universals, and Constraint‐Based Grammar Learning.Jennifer Culbertson, Paul Smolensky & Colin Wilson - 2013 - Topics in Cognitive Science 5 (3):392-424.
    According to classical arguments, language learning is both facilitated and constrained by cognitive biases. These biases are reflected in linguistic typology—the distribution of linguistic patterns across the world's languages—and can be probed with artificial grammar experiments on child and adult learners. Beginning with a widely successful approach to typology (Optimality Theory), and adapting techniques from computational approaches to statistical learning, we develop a Bayesian model of cognitive biases and show that it accounts for the detailed pattern of results of artificial (...)
    Direct download (8 more)  
     
    Export citation  
     
    Bookmark   7 citations  
  6.  52
    Optimization and Quantization in Gradient Symbol Systems: A Framework for Integrating the Continuous and the Discrete in Cognition.Paul Smolensky, Matthew Goldrick & Donald Mathis - 2014 - Cognitive Science 38 (6):1102-1138.
    Mental representations have continuous as well as discrete, combinatorial properties. For example, while predominantly discrete, phonological representations also vary continuously; this is reflected by gradient effects in instrumental studies of speech production. Can an integrated theoretical framework address both aspects of structure? The framework we introduce here, Gradient Symbol Processing, characterizes the emergence of grammatical macrostructure from the Parallel Distributed Processing microstructure (McClelland, Rumelhart, & The PDP Research Group, 1986) of language processing. The mental representations that emerge, Distributed Symbol Systems, (...)
    No categories
    Direct download (7 more)  
     
    Export citation  
     
    Bookmark   8 citations  
  7.  47
    A Bayesian Model of Biases in Artificial Language Learning: The Case of a Word‐Order Universal.Jennifer Culbertson & Paul Smolensky - 2012 - Cognitive Science 36 (8):1468-1498.
  8. The Constituent Structure of Connectionist Mental States.Paul Smolensky - 1987 - Southern Journal of Philosophy Supplement 26:137-60.
  9.  5
    Learnability in Optimality Theory.Bruce Tesar & Paul Smolensky - 2002 - Linguistics and Philosophy 25 (1):65-80.
    Direct download  
     
    Export citation  
     
    Bookmark   20 citations  
  10.  19
    Grammar‐Based Connectionist Approaches to Language.Paul Smolensky - 1999 - Cognitive Science 23 (4):589-613.
    No categories
    Direct download (6 more)  
     
    Export citation  
     
    Bookmark   16 citations  
  11. Constituent Structure and Explanation in an Integrated Connectionist/Symbolic Cognitive Architecture.Paul Smolensky - 1995 - In C. Macdonald (ed.), Connectionism: Debates on Psychological Explanation. Blackwell.
  12. Connectionist, Symbolic, and the Brain.Paul Smolensky - 1987 - AI Review 1:95-109.
     
    Export citation  
     
    Bookmark   8 citations  
  13.  10
    Putting Together Connectionism – Again.Paul Smolensky - 1988 - Behavioral and Brain Sciences 11 (1):59-74.
    A set of hypotheses is formulated for a connectionist approach to cognitive modeling. These hypotheses are shown to be incompatible with the hypotheses underlying traditional cognitive models. The connectionist models considered are massively parallel numerical computational systems that are a kind of continuous dynamical system. The numerical variables in the system correspond semantically to fine-grained features below the level of the concepts consciously used to describe the task domain. The level of analysis is intermediate between those of symbolic cognitive models (...)
    Direct download (5 more)  
     
    Export citation  
     
    Bookmark   8 citations  
  14.  78
    Universals in Cognitive Theories of Language.Paul Smolensky, Emmanuel Dupoux, Nicholas Evans & Stephen C. Levinson - 2009 - Behavioral and Brain Sciences 32 (5):468.
    Generative linguistics' search for linguistic universals (1) is not comparable to the vague explanatory suggestions of the article; (2) clearly merits a more central place than linguistic typology in cognitive science; (3) is fundamentally untouched by the article's empirical arguments; (4) best explains the important facts of linguistic diversity; and (5) illuminates the dominant component of language's nature: biology.
    Direct download (3 more)  
     
    Export citation  
     
    Bookmark   2 citations  
  15.  22
    Harmony in Linguistic Cognition.Paul Smolensky - 2006 - Cognitive Science 30 (5):779-801.
    In this article, I survey the integrated connectionist/symbolic (ICS) cognitive architecture in which higher cognition must be formally characterized on two levels of description. At the microlevel, parallel distributed processing (PDP) characterizes mental processing; this PDP system has special organization in virtue of which it can be characterized at the macrolevel as a kind of symbolic computational system. The symbolic system inherits certain properties from its PDP substrate; the symbolic functions computed constitute optimization of a well-formedness measure called Harmony. The (...)
    No categories
    Direct download (4 more)  
     
    Export citation  
     
    Bookmark   3 citations  
  16.  44
    On the Asymmetrical Difficulty of Acquiring Person Reference in French: Production Versus Comprehension. [REVIEW]Géraldine Legendre & Paul Smolensky - 2012 - Journal of Logic, Language and Information 21 (1):7-30.
    Young French children freely produce subject pronouns by the age of 2. However, by age 2 and a half they fail to interpret 3rd person pronouns in an experimental setting designed to select a referent among three participants (speaker, hearer, and other). No such problems are found with 1st and 2nd person pronouns. We formalize our analysis of these empirical results in terms of direction-sensitive optimizations, showing that uni-directionality of optimization, when combined with non-adult-like constraint rankings, explains the general acquisition (...)
    Direct download (4 more)  
     
    Export citation  
     
    Bookmark   1 citation  
  17.  13
    Subsymbolic Computation Theory for the Human Intuitive Processor.Paul Smolensky - 2012 - In S. Barry Cooper (ed.), How the World Computes. pp. 675--685.
  18.  25
    Kinship Terminology: Polysemy or Categorization?Lotte Hogeweg, Géraldine Legendre & Paul Smolensky - 2010 - Behavioral and Brain Sciences 33 (5):386-387.
    The target article offers an analysis of the categorization of kin types and empirical evidence that cross-cultural universals may be amenable to OT explanation. Since the analysis concerns the structuring of conceptual categories rather than the use of words, it differs from previous OT analyses in lexical semantics in what is considered to be the input and output of optimization.
    Direct download (4 more)  
     
    Export citation  
     
    Bookmark  
  19.  29
    Connectionism and Implementation.Paul Smolensky - 1987 - Behavioral and Brain Sciences 10 (3):492-493.
  20. Connectionism, Constituency and the Language of Thought.Paul Smolensky - 1991 - In Barry M. Loewer & Georges Rey (eds.), Meaning in Mind: Fodor and His Critics. Blackwell.
  21.  17
    In Defense of PTC.Paul Smolensky - 1990 - Behavioral and Brain Sciences 13 (2):407-412.
  22.  6
    Introduction to the 2006 Rumelhart Prize Special Issue Honoring Roger Shepard.Paul Smolensky - 2008 - Cognitive Science 32 (1):1-2.
    No categories
    Direct download (4 more)  
     
    Export citation  
     
    Bookmark  
  23.  19
    Optimization in Neural Networks and in Universal Grammar.Paul Smolensky - unknown
    Direct download  
     
    Export citation  
     
    Bookmark  
  24. On the Projectable Predicates of Connectionist Psychology: A Case for Belief.Paul Smolensky - 1995 - In C. Macdonald & Graham F. Macdonald (eds.), Connectionism: Debates on Psychological Explanation. Blackwell.
  25. The Harmonie Mind. From Neural Computation to Optimality-Theoretic Grammar.Paul Smolensky & Géraldine Legendre - 2009 - Journal for General Philosophy of Science / Zeitschrift für Allgemeine Wissenschaftstheorie 40 (1):141-147.
  26.  43
    The Rumelhart Prize at 10.William Bechtel, Marlene Behrmann, Nick Chater, Robert J. Glushko, Robert L. Goldstone & Paul Smolensky - 2010 - Cognitive Science 34 (5):713-715.