Skip to main content
    • Aa
    • Aa

On the proper treatment of connectionism

  • Paul Smolensky (a1)

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 and neural models. The explanations of behavior provided are like those traditional in the physical sciences, unlike the explanations provided by symbolic models.

Higher-level analyses of these connectionist models reveal subtle relations to symbolic models. Parallel connectionist memory and linguistic processes are hypothesized to give rise to processes that are describable at a higher level as sequential rule application. At the lower level, computation has the character of massively parallel satisfaction of soft numerical constraints; at the higher level, this can lead to competence characterizable by hard rules. Performance will typically deviate from this competence since behavior is achieved not by interpreting hard rules but by satisfying soft constraints. The result is a picture in which traditional and connectionist theoretical constructs collaborate intimately to provide an understanding of cognition.

Linked references
Hide All

This list contains references from the content that can be linked to their source. For a full set of references and notes please see the PDF or HTML where available.

G. Lakoff (1987) Women, fire, and dangerous things: What categories reveal about the mind. University of Chicago Press.

R. J. Nelson (1982) The logic of mind. D. Reidel.

G. Toulouse , S. Dehaene & J.-P. Changeux (1986) A spin glass model of learning by selection. Technical Report, Unite de Neurobiologie Moleculaire, Institut Pasteur, Paris.

Recommend this journal

Email your librarian or administrator to recommend adding this journal to your organisation's collection.

Behavioral and Brain Sciences
  • ISSN: 0140-525X
  • EISSN: 1469-1825
  • URL: /core/journals/behavioral-and-brain-sciences
Please enter your name
Please enter a valid email address
Who would you like to send this to? *



Full text views

Total number of HTML views: 0
Total number of PDF views: 124 *
Loading metrics...

Abstract views

Total abstract views: 653 *
Loading metrics...

* Views captured on Cambridge Core between September 2016 - 24th June 2017. This data will be updated every 24 hours.