How logic emerges from the dynamics of information

It is often claimed that the symbolic approach to information processing is incompatible with connectionism and other associationist modes of representing information. I propose to throw new light on this debate by presenting two examples of how logic can be seen as emerging from an underlying information dynamics. The first example shows how intuitionistic logic results very naturally from an abstract analysis of the dynamics of information. Theanalysis of the dynamics of information. The second example establishes that the activities of a large class of neural networks may be interpreted, on the symbolic level, as nonmonotonic inferences. On the basis of these examples I argue that symbolic and non-symbolic approaches to information can be described in terms of different perspectives on the same phenomenon. Thus, I find that Fodor and Pylyshyn’s claim that connectionist systems cannot be systematic and compositional is based on a misleading interpretation of representations in such systems. 1. TWO PARADIGMS OF COGNITIVE

[1]  Geoffrey E. Hinton.  Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems , 1991 .

[2]  Jeroen Groenendijk,et al.  Dynamic predicate logic , 1991 .

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

[4]  Denise Dellarosa,et al.  The psychological appeal of connectionism , 1988, Behavioral and Brain Sciences.

[5]  P. Smolensky.  Connectionism, Constituency, and the Language of Thought ; CU-CS-416-88 , 1988 .

[6]  Jan van Eijck,et al.  Dynamic interpretation and hoare deduction , 1992, J. Log. Lang. Inf..

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

[8]  Stephen Grossberg,et al.  Absolute stability of global pattern formation and parallel memory storage by competitive neural networks , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[9]  Geoffrey E. Hinton,et al.  Schemata and Sequential Thought Processes in PDP Models , 1986 .

[10]  P. Gärdenfors.  Three levels of inductive inference , 1995 .

[11]  Andrew Woodfield,et al.  The reality of the symbolic and subsymbolic systems , 1988, Behavioral and Brain Sciences.

[12]  Wilfrid S. Sellars,et al.  III.—INFERENCE AND MEANING , 1953 .

[13]  Peter Gärdenfors,et al.  The Dynamics of Belief as a Basis for Logic , 1984, The British Journal for the Philosophy of Science.

[14]  Joel L. Davis,et al.  An Introduction to Neural and Electronic Networks , 1995 .

[15]  N. O. Bernsen,et al.  Systematicity, thought and attention in a distributed connectionist system , 1992 .

[16]  Jeroen Groenendijk,et al.  Dynamic Montague grammar , 1990 .

[17]  P G rdenfors,et al.  Knowledge in flux: modeling the dynamics of epistemic states , 1988 .

[18]  Sarit Kraus,et al.  Nonmonotonic Reasoning, Preferential Models and Cumulative Logics , 1990, Artif. Intell..

[19]  Maarten de Rijke.  Meeting some neighbours , 1992 .

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

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

[22]  Johan van Benthem.  Logic and the flow of information , 1995 .

[23]  Christian Balkenius,et al.  NEURAL MECHANISMS FOR SELF-ORGANIZATION OF EMERGENT SCHEMATA, DYNAMICAL SCHEMA PROCESSING, AND SEMANTIC CONSTRAINT SATISFACTION , 1993 .

[24]  J. Smart.  Neurophilosophy: Toward a unified science of the mind-brain Patricia Smith Churchland. Bradford Books, MIT Press, Cambridge, Massachusetts (1986). xiv + 546 pp. , 1987, Neuroscience.

[25]  Peter Gärdenfors,et al.  Relations between the logic of theory change and nonmonotonic logic , 1989, The Logic of Theory Change.

[26]  R. Thom.  Stabilité structurelle et morphogenèse , 1974 .

[27]  Thomas Jackson,et al.  Neural Computing - An Introduction , 1990 .

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

[29]  Frank Veltman,et al.  Defaults in update semantics , 1996, J. Philos. Log..

[30]  Christian Balkenius,et al.  Nonmonotonic Inferences in Neural Networks , 1991, KR.

[31]  Dov M. Gabbay,et al.  Theoretical Foundations for Non-Monotonic Reasoning in Expert Systems , 1989, Logics and Models of Concurrent Systems.

[32]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[33]  Peter Gärdenfors,et al.  Propositional logic based on the dynamics of belief , 1985, Journal of Symbolic Logic.

[34]  G. Kane.  Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol 1: Foundations, vol 2: Psychological and Biological Models , 1994 .