Issues in Symbol Processing

Abstract : The notion of mind as symbol processor is fundamental to artificial intelligence and cognitive science, but some connectionists are now arguing against it. Eliminative connectionism challenges the validity of formal symbol manipulation as a level of mental description. We review some of the claims that have been made, and argue that most connectionist models, especially those constructed by learning algorithms, are operating at the level of pattern classifiers. Their (rather limited) success using non-symbolic representations demonstrates that they have not yet even approached the tasks which symbol processing models attempt to solve. Continued progress in connectionist research may require reimplementation rather than rejection of the symbolic level. (edc)

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

[2]  David S. Touretzky,et al.  A distributed connectionist representation for concept structures , 1987 .

[3]  Allen Newell,et al.  Harpy, production systems and human cognition , 1978 .

[4]  D. Plaut,et al.  Is Distributed Connectionism Compatible with the Physical Symbol System Hypothesis , 1986 .

[5]  Dana H. Ballard,et al.  Parallel Logical Inference and Energy Minimization , 1986, AAAI.

[6]  Ronald J. Brachman,et al.  An overview of the KL-ONE Knowledge Representation System , 1985 .

[7]  Garrison W. Cottrell,et al.  A connectionist approach to word sense disambiguation , 1988 .

[8]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Ronald J. Brachman,et al.  An Overview of the KL-ONE Knowledge Representation System , 1985, Cogn. Sci..

[10]  E. Stabler.  How are grammers represented? , 1983, Behavioral and Brain Sciences.

[11]  Bart Selman,et al.  Rule-Based Processing in a Connectionist System for Natural Language Understanding , 1985 .

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

[13]  John R. Anderson.  The Architecture of Cognition , 1983 .

[14]  James L. McClelland,et al.  On learning the past-tenses of English verbs: implicit rules or parallel distributed processing , 1986 .

[15]  J. Fodor,et al.  Connectionism and cognitive architecture: A critical analysis , 1988, Cognition.

[16]  Henry S. Thompson,et al.  Computation misrepresented: The procedural/declarative controversy exhumed , 1983, Behavioral and Brain Sciences.

[17]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[18]  Terrence J. Sejnowski,et al.  Parallel Networks that Learn to Pronounce English Text , 1987, Complex Syst..

[19]  S. Pinker,et al.  On language and connectionism: Analysis of a parallel distributed processing model of language acquisition , 1988, Cognition.

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

[21]  John R. Anderson.  Methodologies for studying human knowledge , 1987, Behavioral and Brain Sciences.

[22]  Geoffrey E. Hinton,et al.  Learning and relearning in Boltzmann machines , 1986 .

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

[24]  Jordan B. Pollack,et al.  Massively Parallel Parsing: A Strongly Interactive Model of Natural Language Interpretation , 1988, Cogn. Sci..

[25]  Mark A. Fanty,et al.  Context-free parsing with connectionist networks , 1987 .

[26]  Mark Derthick.  Counterfactual Reasoning with Direct Models , 1987, AAAI.

[27]  Geoffrey E. Hinton,et al.  Symbols Among the Neurons: Details of a Connectionist Inference Architecture , 1985, IJCAI.