Connectionism, Learning and Meaning

Abstract There is an apparent anomaly in the notion that connectionism, which is fundamentally a new technology, has considerable philosophical significance. Nonetheless, connectionism has been widely viewed as having implications for symbol grounding, notions of structured representation and compositionality, as well as the issue of nativism. In this paper, we consider each of these issues in detail and find that the current state of connectionism does not warrant the magnitude of many of the philosophical conclusions drawn from it. We argue that connectionist models are no more 'grounded' than their classical counterparts. In addition, since connectionist representations typically are ascribed content through semantic interpretation based on correlation, connectionism is prone to a number of well known philosophical problems facing any kind of correlational semantics. However, we suggest that philosophy may be ill advised to ignore the development of connectionism, particularly if connectionist systems ...

[1]  Zenon W. Pylyshyn,et al.  Computation and Cognition: Toward a Foundation for Cognitive Science , 1984 .

[2]  Lawrence D. Jackel,et al.  VLSI implementation of a neural network model , 1988, Computer.

[3]  J. Ewert Advances in vertebrate neuroethology , 1982, Trends in Neurosciences.

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

[5]  Stevan Harnad Lost in the hermeneutic hall of mirrors , 1990, J. Exp. Theor. Artif. Intell..

[6]  David R. Dowty,et al.  Introduction to Montague semantics , 1980 .

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

[8]  Fred I. Dretske Explaining Behavior: Reasons in a World of Causes , 1990 .

[9]  Patrick Henry Winston,et al.  The psychology of computer vision , 1976, Pattern Recognit..

[10]  Eric Brill,et al.  Deducing Linguistic Structure from the Statistics of Large Corpora , 1990, HLT.

[11]  S. Stich From folk psychology to cognitive science , 1983 .

[12]  Radu J. Bogdan Belief : form, content, and function , 1986 .

[13]  Thomas Goschke,et al.  The concept of representation and the representation of concepts in connectionist models , 1991 .

[14]  J. Searle,et al.  Is the brain's mind a computer program? , 1990, Scientific American.

[15]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[16]  W. Schneider Connectionism: Is it a paradigm shift for psychology? , 1987 .

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

[18]  James H. Moor,et al.  Knowledge and the Flow of Information. , 1982 .

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

[20]  T. Kuhn The Structure of Scientific Revolutions 2nd edition , 1970 .

[21]  A CarpenterGail,et al.  The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network , 1988 .

[22]  D. Ingle Brain Mechanisms of Visual Localization by Frogs and Toads , 1983 .

[23]  Stevan Harnad,et al.  Categorical Perception and the Evolution of Supervised Learning in Neural Nets , 1991 .

[24]  Ruth Garrett Millikan,et al.  Thoughts Without Laws; Cognitive Science with Content , 1986 .

[25]  P. Churchland A neurocomputational perspective , 1989 .

[26]  Hartry Field Mental representation , 2021, Encyclopedia of Autism Spectrum Disorders.

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

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

[29]  Nick Chater,et al.  WHY ARE CONJUNCTIVE CATEGORIES OVEREXTENDED , 1990 .

[30]  T. Kuhn,et al.  The Structure of Scientific Revolutions. , 1964 .

[31]  N. Chater,et al.  Autonomy, implementation and cognitive architecture: A reply to Fodor and Pylyshyn , 1990, Cognition.

[32]  John E. Moody,et al.  The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems , 1991, NIPS.

[33]  Margaret A. Boden Escaping from the Chinese Room , 1990, The Philosophy of Artificial Intelligence.

[34]  Ralph Linsker,et al.  Self-organization in a perceptual network , 1988, Computer.

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

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

[37]  Douglas L. Medin,et al.  Category cohesiveness, theories, and cognitive archeology. , 1987 .

[38]  S. Harnad Connecting Object to Symbol in Modeling Cognition , 1992 .

[39]  Dennis Norris,et al.  A dynamic-net model of human speech recognition , 1991 .

[40]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

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

[42]  Willard Van Orman Quine,et al.  Word and Object , 1960 .

[43]  S. Laughlin,et al.  Computational neuroethology: a provisional manifesto , 1991 .

[44]  M. R. D'Amato,et al.  The person concept in monkeys (Cebus apella) , 1988 .

[45]  Garrison W. Cottrell Toward connectionist semantics , 1987, TINLAP '87.

[46]  Steven Pinker,et al.  Language learnability and language development , 1985 .

[47]  Nick Chater,et al.  FINDING LINGUISTIC STRUCTURE WITH RECURRENT NEURAL NETWORKS , 1992 .

[48]  Stephen José Hanson,et al.  What connectionist models learn: Learning and representation in connectionist networks , 1990, Behavioral and Brain Sciences.

[49]  Adrian Cussins,et al.  The Connectionist Construction of Concepts , 1990, The Philosophy of Artificial Intelligence.

[50]  J. Altham Naming and necessity. , 1981 .

[51]  D. Medin,et al.  The role of theories in conceptual coherence. , 1985, Psychological review.

[52]  D. Stampe Toward a Causal Theory of Linguistic Representation , 1977 .

[53]  William P. Alston,et al.  Knowledge and the Flow of Information , 1985 .

[54]  D. Medin,et al.  Context and structure in conceptual combination , 1988, Cognitive Psychology.

[55]  J. Hampton Overextension of Conjunctive Concepts: Evidence for a Unitary Model of Concept Typicality and Class Inclusion , 1988 .

[56]  A. Stolcke Syntactic Category Formation with Vector Space Grammars , 1991 .

[57]  Patrick Henry Winston,et al.  Learning structural descriptions from examples , 1970 .

[58]  Daniel N. Osherson,et al.  Systems That Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists , 1990 .

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

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

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

[62]  Steven Pinker,et al.  On language and connectionism , 1988 .

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

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

[65]  Scott E. Fahlman,et al.  An empirical study of learning speed in back-propagation networks , 1988 .

[66]  Jerry A. Fodor,et al.  A Theory of Content and Other Essays. , 1992 .

[67]  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.

[68]  Michael G. Dyer Finding lost minds , 1990, J. Exp. Theor. Artif. Intell..

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

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

[71]  U. Neisser Concepts and Conceptual Development: Ecological and Intellectual Factors in Categorization , 1989 .

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

[73]  Michael Cohen,et al.  Reference and Essence , 1984 .

[74]  Douglas B. Lenat,et al.  Knowledge-based systems in artificial intelligence , 1981 .

[75]  Lawrence W. Barsalou,et al.  The instability of graded structure: implications for the nature of concepts , 1987 .

[76]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[77]  Stevan Harnad,et al.  Minds, machines and Searle , 1989, J. Exp. Theor. Artif. Intell..

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

[79]  R. Kirk Language, Thought, and Other Biological Categories , 1985 .

[80]  Jon Barwise,et al.  2. Unburdening the Language of Thought , 1987 .

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

[82]  N. Chater,et al.  Against Logicist Cognitive Science , 1991 .

[83]  J. E. Creighton,et al.  The Philosophical Review , 1901 .

[84]  P. Moser Remnants of Meaning , 1988 .

[85]  A. Clark,et al.  Connectionism in Context , 1992, Artificial Intelligence and Society.

[86]  Massimo Piattelli-Palmarini,et al.  Language and Learning: The Debate Between Jean Piaget and Noam Chomsky , 1980 .

[87]  Frederick Jelinek,et al.  Basic Methods of Probabilistic Context Free Grammars , 1992 .

[88]  James L. McClelland,et al.  Finite State Automata and Simple Recurrent Networks , 1989, Neural Computation.

[89]  Alex M. Andrew,et al.  Computation and Cognition: Towards A Foundation for Cognitive Science, by Zenon W. Pylyshyn, MIT Press, Cambridge, Mass., xxiii + 292 pp., £26.15 , 1985, Robotica.

[90]  P M Churchland,et al.  Could a machine think? , 1990, Scientific American.

[91]  E. Feigenbaum 13 – Information Processing and Memory , 1970 .

[92]  G. Lakoff Cognitive models and prototype theory. , 1987 .

[93]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[94]  James L. McClelland,et al.  James L. McClelland, David Rumelhart and the PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition . Vol. 1. Foundations . Vol. 2. Psychological and biological models . Cambridge MA: M.I.T. Press, 1987. , 1989, Journal of Child Language.

[95]  R. Herrnstein,et al.  Natural concepts in pigeons. , 1976, Journal of experimental psychology. Animal behavior processes.

[96]  Nick Chater,et al.  Information and information processing , 1990 .

[97]  MICHAEL G. DYER,et al.  Intentionality and computationalism: minds, machines, Searle and Harnad , 1990, J. Exp. Theor. Artif. Intell..

[98]  R. Weale Analysis of Visual Behaviour , 1983 .

[99]  W. Pitts,et al.  What the Frog's Eye Tells the Frog's Brain , 1959, Proceedings of the IRE.

[100]  D. Chalmers Why Fodor and Pylyshyn Were Wrong: The Simplest Refutation , 1990 .

[101]  Lars Niklasson,et al.  Connectionism and the Issues of Compositionality and Systematicity , 1992 .

[102]  Rita Nolan A Theory of Content and Other Essays , 1992 .

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

[104]  S. Pinker Formal models of language learning , 1979, Cognition.

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

[106]  Roger Smook Explaining Behaviour: Reasons in a World of Causes , 1989 .

[107]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[108]  T. Horgan,et al.  Connectionism and the Philosophy of Mind , 1991 .

[109]  James L. McClelland,et al.  Learning Subsequential Structure in Simple Recurrent Networks , 1988, NIPS.