Networks are not ‘hidden rules’

  title={Networks are not ‘hidden rules’},
  author={M. S. Seidenberg and J. L. Elman},
  journal={Trends in Cognitive Sciences},
  • M. S. Seidenberg, J. L. Elman
  • Published 1999
  • Psychology, Medicine
  • Trends in Cognitive Sciences
  • The grammatical morphology of Hebrew-speaking children with specific language impairment sensory and language processing in language-Does learning a language involve formulating rules or gathering statistics? Marcus and colleagues offered two pieces of evidence bearing on this debate 1. Their behavioral studies were taken as evidence that babies form 'alge-braic rules' and their attempt to model this behavior suggested that it is incompatible with the properties of a 'popular' class of… CONTINUE READING

    Topics from this paper.

    Pre-Wiring and Pre-Training: What Does a Neural Network Need to Learn Truly General Identity Rules?
    • 12
    • Open Access
    The Statistical Brain: Reply to Marcus’ The Algebraic Mind
    • 11
    • Highly Influenced
    • Open Access
    Modeling Infant Learning via Symbolic Structural Alignment
    • 59
    • Open Access
    Infant artificial language learning and language acquisition
    • 423
    • Open Access
    The role of salience in the extraction of algebraic rules.
    • 123
    • Open Access


    Publications referenced by this paper.
    Rethinking Eliminative Connectionism
    • 276
    • Open Access
    Rule learning by seven-month-old infants.
    • 936
    • Open Access
    Do Infants Learn Grammar with Algebra or Statistics?
    • 58
    • Open Access
    The discovery of spoken language
    • 753
    Reply to Christiansen and Curtin
    • 17