How connectionism can change AI and the way we think about ourselves

Abstract In this paper we discuss some fundamentals of “conventional” or “symbolic ” artificial intelligence (AI) and how connectionism, if done properly, can provide some genuinely novel aspects. We show some evidence against the traditional approach when viewed as a plausible model of animate intelligence. We also show that connectionist models appear to be much closer to an adequate model of “natural” behavior. Furthermore, we discuss possible impacts of connectionism on AI as afield of research and, beyond that, on how we think about our own mind. Many questions, however, remain open to permit a clear forecast of where the research will lead us.

[1]  Terry Winograd,et al.  Understanding computers and cognition , 1986 .

[2]  John R. Searle,et al.  Minds, brains, and programs , 1980, Behavioral and Brain Sciences.

[3]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[4]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[5]  Terry Winograd,et al.  Understanding computers and cognition - a new foundation for design , 1987 .

[6]  Joachim Diederich,et al.  Connectionist Recruitment Learning , 1988, ECAI.

[7]  Isabelle Guyon,et al.  Neural Network Recognizer for Hand-Written Zip Code Digits , 1988, NIPS.

[8]  G. Lakoff,et al.  Women, Fire, and Dangerous Things: What Categories Reveal about the Mind , 1988 .

[9]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[10]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[11]  Noam Chomsky.  Reflections on Language. , 1977 .

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

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

[14]  Stevan Harnad,et al.  Symbol grounding problem , 1990, Scholarpedia.

[15]  David Zipser,et al.  Feature Discovery by Competive Learning , 1986, Cogn. Sci..

[16]  Mark A. Fanty,et al.  Computing with structured neural networks , 1988, Computer.

[17]  Terrence J. Sejnowski,et al.  Analysis of hidden units in a layered network trained to classify sonar targets , 1988, Neural Networks.

[18]  E. V. Glasersfeld.  Wissen, Sprache und Wirklichkeit , 1987 .

[19]  Noam Chomsky.  Review of B.F. Skinner, Verbal Behavior , 1959 .

[20]  P. Smolensky.  On the proper treatment of connectionism , 1988, Behavioral and Brain Sciences.

[21]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

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

[23]  Noel E. Sharkey,et al.  Connectionist Representations for Natural Language: Old and New , 1990, ÖGAI.

[24]  Georg Dorffner,et al.  A sub-symbolic connectionist model of basic language functions , 1989 .

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

[26]  Allen Newell,et al.  Computer science as empirical inquiry: symbols and search , 1976, CACM.

[27]  D. Massaro.  Some criticisms of connectionist models of human performance , 1988 .

[28]  Richard Kendall Miller,et al.  Neural Net Applications and Products , 1990 .

[29]  H. Maturana,et al.  Autopoiesis and Cognition , 1980 .

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

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

[32]  Noam Chomsky,et al.  वाक्यविन्यास का सैद्धान्तिक पक्ष = Aspects of the theory of syntax , 1965 .

[33]  Stephen I. Gallant,et al.  Connectionist expert systems , 1988, CACM.