Connectionism, Systematicity, and the Frame Problem

This paper investigates connectionism's potential to solve the frame problem. The frame problem arises in the context of modelling the human ability to see the relevant consequences of events in a situation. It has been claimed to be unsolvable for classical cognitive science, but easily manageable for connectionism. We will focus on a representational approach to the frame problem which advocates the use of intrinsic representations. We argue that although connectionism's distributed representations may look promising from this perspective, doubts can be raised about the potential of distributed representations to allow large amounts of complexly structured information to be adequately encoded and processed. It is questionable whether connectionist models that are claimed to effectively represent structured information can be scaled up to a realistic extent. We conclude that the frame problem provides a difficulty to connectionism that is no less serious than the obstacle it constitutes for classical cognitive science.

[1]  L. Shastri,et al.  From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony , 1993, Behavioral and Brain Sciences.

[2]  David Kirsh,et al.  When is Information Explicitly Represented , 1990 .

[3]  J. Fodor Psychosemantics: The Problem of Meaning in the Philosophy of Mind , 1988 .

[4]  Tim van Gelder,et al.  Defining ‘Distributed Representation’ , 1992 .

[5]  Willem F. G. Haselager,et al.  Cognitive Science and Folk Psychology: The Right Frame of Mind , 1997 .

[6]  Risto Miikkulainen,et al.  Natural Language Processing With Modular PDP Networks and Distributed Lexicon , 1991, Cogn. Sci..

[7]  Geoffrey E. Hinton Preface to the Special Issue on Connectionist Symbol Processing , 1990 .

[8]  高梨 克也 Cognitive Science and Folk Psychology : The Right Frame of Mind. : W.F.G.Haselager (Sage Publications,1997) , 1999 .

[9]  T. Horgan,et al.  Connectionism and the Philosophy of Psychology , 1996 .

[10]  Morten H. Christiansen,et al.  Generalization and connectionist language learning , 1994 .

[11]  D. Freidman,et al.  The Engine of Reason, the Seat of the Soul: A Philosophical Journey into the Brain , 1996, Journal of Cognitive Neuroscience.

[12]  John McCarthy,et al.  SOME PHILOSOPHICAL PROBLEMS FROM THE STANDPOINT OF ARTI CIAL INTELLIGENCE , 1987 .

[13]  Z. Pylyshyn Robot's Dilemma: The Frame Problem in Artificial Intelligence , 1987 .

[14]  T. Gelder,et al.  On Being Systematically Connectionist , 1994 .

[15]  David J. Chalmers,et al.  Syntactic Transformations on Distributed Representations , 1990 .

[16]  James H. Fetzer The frame problem: artificial intelligence meets David Hume , 1990 .

[17]  Zenon W. Pylyshyn,et al.  Connectionism and cognitive architecture , 1993 .

[18]  Jerome A. Feldman,et al.  Neural Representation of Conceptual Knowledge. , 1986 .

[19]  P. Churchland A Neurocomputational Perspective: The Nature of Mind and the Structure of Science , 1989 .

[20]  David J. Chalmers,et al.  Connectionism and compositionality: Why Fodor and Pylyshyn were wrong , 1993 .

[21]  Mark Derthick,et al.  Mundane Reasoning by Settling on a Plausible Model , 1990, Artif. Intell..

[22]  P. Churchland,et al.  The Engine of Reason, The Seat of the Soul: A Philosophical Journey into the Brain , 1995 .

[23]  P. Hayes Commentary on “The frame problem: artificial intelligence meets David Hume” , 1990 .

[24]  D. Rumelhart,et al.  Philosophy and Connectionist Theory , 1991 .

[25]  W. Bechtel,et al.  Connectionism and the Mind , 1991 .

[26]  Gustav Bergmann,et al.  PHILOSOPHICAL STUDIES , 1927, Philosophy.

[27]  Steven Phillips,et al.  Connectionism and the problem of systematicity , 1995 .

[28]  J. Fodor,et al.  Connectionism and the problem of systematicity: Why Smolensky's solution doesn't work , 1990, Cognition.

[29]  Andy Clark The Presence of a Symbol , 1992 .

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

[31]  K. Butler,et al.  Connectionism, classical cognitivism and the relation between cognitive and implementational levels of analysis , 1993 .

[32]  Tim van Gelder,et al.  Compositionality: A Connectionist Variation on a Classical Theme , 1990, Cogn. Sci..

[33]  A. Clark,et al.  Trading spaces: Computation, representation, and the limits of uninformed learning , 1997, Behavioral and Brain Sciences.

[34]  John E. Hummel,et al.  Distributing structure over time , 1993, Behavioral and Brain Sciences.

[35]  Robert F. Hadley Systematicity revisited : reply to Christiansen and Chater and Niklasson and van Gelder , 1994 .

[36]  Jordan B. Pollack,et al.  Recursive Distributed Representations , 1990, Artif. Intell..

[37]  Murray Shanahan Solving the frame problem - a mathematical investigation of the common sense law of inertia , 1997 .

[38]  Robert F. Hadley Systematicity in Connectionist Language Learning , 1994 .

[39]  Hubert L. Dreyfus,et al.  Mind over Machine: The Power of Human Intuition and Expertise in the Era of the Computer , 1987, IEEE Expert.

[40]  J. Elman Learning and development in neural networks: the importance of starting small , 1993, Cognition.

[41]  Robert F. Hadley The “explicit-implicit” distinction , 1995, Minds and Machines.

[42]  Hubert L. Dreyfus,et al.  How to stop worrying about the frame problem even though it's computationally insoluble , 1987 .

[43]  Associationism: Not the Cliff Over Which to Push Connectionism , 1994 .

[44]  J. Elman Distributed Representations, Simple Recurrent Networks, And Grammatical Structure , 1991 .

[45]  P. Smolensky THE CONSTITUENT STRUCTURE OF CONNECTIONIST MENTAL STATES: A REPLY TO FODOR AND PYLYSHYN , 2010 .

[46]  Terrence J. Sejnowski,et al.  The Computational Brain , 1996, Artif. Intell..

[47]  K. Holyoak Symbolic connectionism: Toward third-generation theories of expertise. , 1991 .

[48]  T. Gelder,et al.  Classical Questions, Radical Answers: Connectionism and the Structure of Mental Representations , 1991 .