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.

D. H. Ackley , G. E. Hinton & T. J. Sejnowski (1985) A learning algorithm for Boltzmann machines. Cognitive Science 9:147–69.

D. Z. Anderson (1986) Coherent optical eigenstate memory. Optics Letters 11:5658.

J. A. Anderson , J. W. Silverstein & S. A. Ritz (1977) Distinctive features, categorical perception, and probability learning: Some applications of a neural model. Psychological Review 84:413–51.

J. Barwise (1986) Information and circumstance. Notre Dame Journal of Formal Logic 27(3):324–38.

W. Bechtel (1985) Realism, instrumentalism, and the intentional stance. Cognitive Science 9:473–97.

T. Burge (1986) Individualism and psychology. Philosophical Review 95(1): 345.

R. T. Cox (1946) Probability, frequency, and reasonable expectation. American Journal of Statistical Physics 14:113.

D. Davidson (1970) Mental events. In; Experience and theory, ed. L. Foster & J. W. Swanson . University of Massachusetts Press.

G. S. Dell (1985) Positive feedback in hierarchical connectionist models: Applications to language production. Cognitive Science 9:323.

J. A. Feldman & D. H. Ballard (1982) Connectionist models and their properties. Cognitive Science 6:205–54.

J. A. Fodor (1986) Information and association. Notre Dame Journal of Formal Logic 27:307–23.

J. A. Fodor & Z. W. Pylyshyn (1988) Connectionism & cognitive architecture: A critical analysis. Cognition 28: 371.

W. J. Freeman (1975) Mass action in the nervous system. Academic Press.

S. Grossberg (1976) Adaptive pattern classification and universal recoding. Biological Cybernetics 23:121–34; 187–202 (in two parts).

S. Grossberg (1987) Competitive learning: From interactive activation to adaptive resonance. Cognitive Science 11:2363.

S. Grossberg ed. (1987a) The adaptive brain I: Cognition, learning, reinforcement, and rhythm. North-Holland,

S. Grossberg & E. Mingolla (1985) Neural dynamics of form perception: Boundary completion, illusory figures, and neon color spreading. Psychological Review 92:173211.

S. Grossberg & G. Stone (1986) Neural dynamics of word recognition and recall: Attentional priming, learning, and resonance. Psychological Review 93:4674.

S. Grossberg (1986) Neural dynamics of attention switching and temporal order information in short-term memory. Memory and Cognition 14:451–68.

M. Halle (1962) Phonology in generative grammar. Word 18:5472.

J. J. Hopfield (1982) Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Science 79:2554–58.

J. J. Hopfield (1984) Neurons with graded response have collective properties like those of two-state neurons. Proceedings of the National Academy of Sciences, USA 81:3088–92.

S. M. Kosslyn (1987) Seeing and imaging in the cerebral hemispheres: A computational approach. Psychological Review 94:148–75.

J. H. Larkin , J. McDermott , D. P. Simon & H. A. Simon (1980) Models of competence in solving physics problems. Cognitive Science 4:317–45.

A. R. Luria (1966) Higher cortical functions in man. Basic Books.

W. G. Lycan (1981) Form, function, and feel. Journal of Philosophy 78:2450.

D. Marr (1982) Vision. W. H. Freeman.

J. L. McClelland & D. E. Rumelhart (1981) An interactive activation model of context effects in letter perception: Part I. An account of th e basic findings. Psychological Review 88:375407.

J. Moran & R. Desimone (1985) Selective attention gates visual processing in the extrastriate cortex. Science 229:782–84.

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

A. Newell (1980) Physical symbol systems. Cognitive Science 4:135–83.

A. Newell , J. C. Shaw & H. A. Simon (1958) Elements of a theory of human problem solving. Psychological Review 65:151–66.

A. Newell & H. A. Simon (1976) Computer science as empirical inquiry: Symbols and search. Communications of the Association for Computing Machinery 19:113–26.

G. C. Oden (1987) Concept, knowledge, and thought. Annual Review of Psychology 38:203–28.

S. Pinker & A. Prince (1988) On language and connectionism: Analysis of a parallel distributed processing model of language acquisition. Cognition 28: 73193.

A. Reeves & G. Sperling (1986) Attentional theory of order information in short-term memory. Psychological Review 93:180206.

G. Rey (1983) Concepts and stereotypes. Cognition 15:237–62.

G. Rey (1985) Concepts and conceptions. Cognition 19:297303.

D. E. Rumelhart & J. L. McClelland (1982) An interactive activation model of context effects in letter perception: Part 2. The contextual enhancement effect and some tests and extensions of the model. Psychological Review 89:6094.

R. C. Schank (1972) Conceptual dependency: A theory of natural language understanding. Cognitive Psychology 3(4):552631.

T. J. Sejnowski (1976) On the stochastic dynamics of neuronal interactions. Biological Cybernetics 22:203–11.

R. N. Shepard (1962) The analysis of proximities: Multidimensional scaling with an unknown distance function. I & II. Psychometrika 27:125–40, 219–46.

R. N. Shepard (1964) Review of Computers and thought (ed. E. Feigenbaum & J. Feldman ). Behavioral Science 9:5765.

R. N. Shepard (1984) Ecological constraints on internal representation: Resonant kinematics of perceiving, imagining, thinking, and dreaming. Psychological Review 91:417–47.

R. N. Shepard & J. Metzler (1971) Mental rotation of three-dimensional objects. Science 171:701–3.

R. M. Shiffrin & W. Schneider (1977) Controlled an d automatic human information processing. II. Perceptual learning. Psychological Review 84:127–90.

S. Smale (1987) On the topology of algorithms, I. Journal of Complexity 3:8189.

P. Smolensky (1987a) Connectionist AI, symbolic Al, and the brain. Artificial Intelligence Review 1:95109.

A. Tversky & D. Kahneman (1983) Extensional versus intuitive reasoning: The conjunction fallacy in probability judgment. Psychological Review 90:293315.

S. Ullman (1984) Visual routines. Cognition 18:97159.

M. M. Waldrop (1984) Artificial intelligence in parallel. Science 225:608–10.

D. L. Waltz (1978) An English language question answering system for a large relational database. Communications of the Association for Computing Machinery 21:526–39.

D. L. Waltz & J. B. Pollack (1985) Massively parallel parsing: A strongly interactive model of natural language interpretation. Cognitive Science 9:5174.

Y. A. Wilks (1978) Making preference more active. Artificial Intelligence 11:197223.

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? *