Connectionist AI, symbolic AI, and the brain

Connectionist AI systems are large networks of extremely simple numerical processors, massively interconnected and running in parallel. There has been great progress in the connectionist approach, and while it is still unclear whether the approach will succeed, it is also unclear exactly what the implications for cognitive science would be if it did succeed. In this paper I present a view of the connectionist approach that implies that the level of analysis at which uniform formal principles of cognition can be found is the subsymbolic level, intermediate between the neural and symbolic levels. Notions such as logical inference, sequential firing of production rules, spreading activation between conceptual units, mental categories, and frames or schemata turn out to provide approximate descriptions of the coarse-grained behaviour of connectionist systems. The implication is that symbol-level structures provide only approximate accounts of cognition, useful for description but not necessarily for constructing detailed formal models.

[1]  Allen Newell,et al.  Human Problem Solving. , 1973 .

[2]  Gary S. Dell,et al.  Positive Feedback in Hierarchical Connectionist Models: Applications to Language Production , 1988, Cogn. Sci..

[3]  Allen Newell,et al.  Physical Symbol Systems , 1980, Cogn. Sci..

[4]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[5]  J. Fodor,et al.  The Language of Thought , 1980 .

[6]  Drew McDermott,et al.  Non-Monotonic Logic I , 1987, Artif. Intell..

[7]  Jerome A. Feldman,et al.  Rochester Connectionist Papers: 1979-1985 , 1985 .

[8]  James L. McClelland,et al.  Parallel Distributed Processing: Explorations in the Microstructure of Cognition : Psychological and Biological Models , 1986 .

[9]  Allen Newell,et al.  The Knowledge Level , 1989, Artif. Intell..

[10]  Paul Smolensky.  Neural and Conceptual Interpretations of Parallel Distributed Processing Models , 1986 .

[11]  James L. McClelland,et al.  An interactive activation model of context effects in letter perception: Part 2. The contextual enhancement effect and some tests and extensions of the model. , 1982, Psychological review.

[12]  Paul Smolensky,et al.  Schema Selection and Stochastic Inference in Modular Environments , 1983, AAAI.

[13]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

[14]  George Boole,et al.  An Investigation of the Laws of Thought: Frontmatter , 2009 .

[15]  James L. McClelland,et al.  An interactive activation model of context effects in letter perception: I. An account of basic findings. , 1981 .

[16]  Jerome A. Feldman,et al.  Connectionist Models and Their Applications: Introduction , 1985 .

[17]  Geoffrey E. Hinton,et al.  Parallel Models of Associative Memory , 1989 .

[18]  D. O. Hebb,et al.  The organization of behavior , 1988 .

[19]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .