Jump to ContentJump to Main Navigation
Show Summary Details
More options …

Open Philosophy

Editor-in-Chief: Harman, Graham


Covered by:
DOAJ - Directory of Open Access Journals
ERIH PLUS

Open Access
Online
ISSN
2543-8875
See all formats and pricing
More options …

The Curious Case of Connectionism

Istvan S. N. Berkeley
Published Online: 2019-08-12 | DOI: https://doi.org/10.1515/opphil-2019-0018

Abstract

Connectionist research first emerged in the 1940s. The first phase of connectionism attracted a certain amount of media attention, but scant philosophical interest. The phase came to an abrupt halt, due to the efforts of Minsky and Papert (1969), when they argued for the intrinsic limitations of the approach. In the mid-1980s connectionism saw a resurgence. This marked the beginning of the second phase of connectionist research. This phase did attract considerable philosophical attention. It was of philosophical interest, as it offered a way of counteracting the conceptual ties to the philosophical traditions of atomism, rationalism, logic, nativism, rule realism and a concern with the role symbols play in human cognitive functioning, which was prevalent as a consequence of artificial intelligence research. The surge in philosophical interest waned, possibly in part due to the efforts of some traditionalists and the so-called black box problem. Most recently, what may be thought of as a third phase of connectionist research, based on so-called deep learning methods, is beginning to show some signs of again exciting philosophical interest.

Keywords: Connectionism; Neural Networks; History; Philosophy

Refrences

  • Abraham, Tara. Rebel Genius: Warren S. McCulloch’s Transdisciplinary Life in Science, Cambridge, Mass.: M.I.T. Press, 2016.Google Scholar

  • Aizawa, Ken. “Connectionism and Artificial Intelligence: History and Philosophical Interpretations” Journal of Experimental and Theoretical Artificial Intelligence, 4 (1992), 295–313.Google Scholar

  • Aizawa, Ken. “Representations without Rules, Connectionism and the Syntactic Argument”. Synthese, 101:3 (1994), 465–492.Google Scholar

  • Aizawa, Ken. The Systematicity Arguments, Boston, Mass.: Kluwer Academic, 2003.Google Scholar

  • Aizawa, Ken. “Warren McCulloch’s Turn to Cybernetics: What Walter Pitts Contributed”. Interdisciplinary Science Review, 37:3 (2012), 206–217.Google Scholar

  • Anderson, James A. and Rosenfield, Edward (Eds.) (1998), Talking Nets: An Oral History of Neural Networks, Cambridge, Mass.: M.I.T. Press, 1998.CrossrefGoogle Scholar

  • Arnold, Solvi, Suzuki, Reiji, and Arita, Takaya. “Selection for Representation in Higher-Order Adaption”, Minds and Machines, 25:1 (2015), 73–95.Google Scholar

  • Bechtel, William. “Contemporary Connectionism: Are the New Parallel Distributed Processing Models Cognitive or Associationist?” Behaviorism, 13 (1985), 53–61.Google Scholar

  • Bechtel, William and Abrahamsen, Adelle. Connectionism and the Mind: An Introduction to Parallel Processing in Networks, Cambridge, Mass.: Basil Blackwell, 1991.Google Scholar

  • Berkeley, Istvan, Dawson, Michael, Medler, David, Schopflocher, Donald and Hornsby, Loraine. „Density Plots of Hidden Unit Activations Reveal Interpretable Bands“, Connection Science, 7:2 (1995) 167–186.CrossrefGoogle Scholar

  • Berkeley, Istvan. “What the #$*%! Is a Subsymbol?” Minds and Machines, 10:1 (2000), 1–13.CrossrefGoogle Scholar

  • Berkeley, Istvan, and Gunay, Cengiz. “Conducting Banding Analysis with Trained Networks of Sigmoid Units”, Connection Science, 16:2 (2004), 119–128.CrossrefGoogle Scholar

  • Berkeley, Istvan. “What the <0.70, 1.17, 0.99, 1.07> is a Symbol?” Minds and Machines, 18 (2008), 93–105.Google Scholar

  • Berkeley, Istvan, and Raine, Roxanne. (2011), “An Old Fashioned Connectionist Approach to a Cajun Chord Change Problem”, Connection Science, 23:3 (2011), 209–218,CrossrefGoogle Scholar

  • Boden, Margaret. Mind as Machine: A History of Cognitive Science, Oxford: Oxford U.P, 2006.Google Scholar

  • Browne, Antony. (Ed.) Neural Network Analysis, Architectures and Applications, Philadelphia, PA: Institute of Physics, 1997.Google Scholar

  • Buckner, Cameron. “Empiricism Without Magic: Tranformational Abstraction in Deep Convolutional Neural Networks”, Synthese, 195:12 (2018), 5339–5372. https://doi.org/10.1007/s11229-018-01949-1.Crossref

  • Bullinaria, John. “Analyzing the Internal Representations of Trained Neural Networks”. In Neural Network Analysis, Architectures and Applications, edited by Antony Browne, (1997), 3–26.Google Scholar

  • Chalmers, David. “Syntactic Transformations on Distributed Representations” in Connection Science, 2:1–2 (1990), 53–62.Google Scholar

  • Chalmers, David. “Connectionism and Compositionality: Why Fodor and Pylyshyn were Wrong”, in Philosophical Psychology, 6:3 (1993), 305–320.Google Scholar

  • Charniak, Eugene. Introduction to Deep Learning, Cambridge Mass.: M.I.T. Press, 2019.Google Scholar

  • Cireşan Dan, Meier Ueli, Masci, Jonathan, Schmidhuber Jurgen. “Multi-column deep neural network for traffic sign classification”. Neural Networks 32 (2012), 333–338.CrossrefGoogle Scholar

  • Chomsky, Noam. Aspects of a Theory of Syntax, Cambridge, Mass.: M.I.T. Press, 1965.Google Scholar

  • Churchland, Paul. M. “On the Nature of Theories: A Neurocomputational Perspective” in Minnesota Studies in the Philosophy of Science 14 (1989), 59–101.Google Scholar

  • Churchland, Patricia S. and Sejnowski, Terrence. “Neural Representation and Neural Computation”, Philosophical Perspectives, 4 (1990), 343–382.CrossrefGoogle Scholar

  • Clark, Andy. Microcognition: Philosophy, Cognitive Science and Parallel Distributed Processing, Cambridge, Mass.: M.I.T. Press, 1989.Google Scholar

  • Clark, Andy. “A review of “Simple Minds“ by D. Lloyd, 1989, M.I.T. Press, London”, Connection Science, 1:4 (1989), 418–421.Google Scholar

  • Clark, Andy. “Representation, Development and Situated Connectionism”, Connection Science, 4:3–4 (1992), 171–174.CrossrefGoogle Scholar

  • Clark, Andy. and Lutz, Rudi. (Eds.) Connectionism in Context (Human Centered Systems), New York, NY: Springer-Verlag, 1992.Google Scholar

  • Davis, Martin. “Two Notions of Implicit Rules”, in Philosophical Perspectives, 9 (1995), 153–183.Google Scholar

  • Davis, Stephen. (Ed.) Connectionism: Theory and Practice, New York, NY: Oxford U.P. 1992.Google Scholar

  • Dawson, Michael and Schopflocher, Don. “Modifying the Generalized Delta Rule to Train Networks of Non-Monotonic Processors for Pattern Classification” Connection Science, 4 (1992), 19–31.Google Scholar

  • Dawson, Michael. Medler, David. and Berkeley, Istvan. “PDP Networks Can Provide Models That Are Not Mere Implementations of Classical Theories” Philosophical Psychology, 10:1 (1997), 25–40.CrossrefGoogle Scholar

  • Dawson, Michael. Minds and Machines: Connectionism and Psychological Modeling, Hoboken, NJ: Wiley-Blackwell, 2008.Google Scholar

  • Dreyfus, Herbert. and Dreyfus, Stuart. “Making a Mind verses Modeling a Brain: Artificial Intelligence Back at a Branchpoint” in S. Graubard (ed.) The Artificial Intelligence Debate: False Starts, Real Foundations, edited by Graubard, Stephen, Cambridge, Mass.: M.I.T. Press, 1988.Google Scholar

  • Elman, Jeff, Bates, Elizabeth, Johnson, Mark, Karmiloff-Smith, Annette, Parisi, Domenico, and Plunkett, Kim. Rethinking Innateness: A Connectionist Perspective on Development, Cambridge, Mass.: M.I.T. Press, 1996.Google Scholar

  • Fodor, Jerry. The Language of Thought, Cambridge, Mass.: Harvard U.P., 1975.Google Scholar

  • Fodor, Jerry. The Modularity of Mind, Cambridge, Mass.: M.I.T. Press, 1983.Google Scholar

  • Fodor, Jerry. “Discussion: Connectionism and the Problem of Systematicity (continued): Why Smolensky’s Solution Still does not Work.” Cognition, 62:1 (1997), 109–119.Google Scholar

  • Fodor, Jerry and Pylyshyn, Zenon. “Connectionism and Cognitive Architecture: A Critical Analysis”, Cognition, 28 (1988), 3–71.Google Scholar

  • Fodor, Jerry and McLaughlin, Brian. “Connectionism and the Problem of Systematicity: Why Smolensky‘s Solution Doesn‘t Work”, Cognition, 35 (1990), 183–204.CrossrefGoogle Scholar

  • Haugeland, John. Artificial Intelligence: The Very Idea, Cambridge, Mass.: M.I.T. Press, 1985.Google Scholar

  • Heicht-Nielson, Robert. Neurocomputation, New York, NY: Addison-Wesley Pub. Co., 1990.Google Scholar

  • Hopfield, John. “Neural Networks and Physical Systems with Emergent Collective Computational Abilities”, Proceedings of the National Academy of the Sciences, USA, 79 (1982), 2554–2558.Google Scholar

  • Hopfield, John. “Neurons with Graded Response have Collective Computational Properties Like Those of Two-State Neurons”, Proceedings of the National Academy of Sciences, USA, 81 (1984), 3088–3092.CrossrefGoogle Scholar

  • Horgan, Terence and Tienson, John. “Spindel Conference 1987: Connectionism and The Philosophy of Mind”, The Southern Journal of Philosophy, Vol. XXVI, Supplement, (1987).Google Scholar

  • Horgan, Terence. and Tienson, John. “Representations Without Rules”, in Philosophical Topics, 17 (1989), 147–174.Google Scholar

  • Horgan, Terence. and Tienson, John. (Eds.) Connectionism and The Philosophy of Mind, New York, NY: Springer, 1991.Google Scholar

  • Horgan, Terence. and Tienson, John. “Settling into a New Paradigm”, Connectionism and The Philosophy of Mind, edited by Horgan, Terence and Tienson, John (1991), 241–260.Google Scholar

  • Klahr, David, Langley, Pat and Neches, Robert (eds.), Production System Models of Learning and Development, Cambridge, Mass.: MIT Press, 1987.Google Scholar

  • Lloyd, Dan. Simple Minds, Cambridge, Mass.: M.I.T. Press, 1989.Google Scholar

  • Lovecraft, Howard, P. H. P. Lovecraft, The Fiction, Complete and Unabridged, New York: Barnes and Noble, 2008.Google Scholar

  • Marr, David. Vision: A Computational Approach, San Francisco, CA: Freeman & Co., 1982.Google Scholar

  • McClelland, Jay and Rumelhart, David. Explorations in Parallel Distributed Processing, Cambridge, Mass.: M.I.T. Press, 1986.Google Scholar

  • McClelland, Jay, Rumelhart, David and Hinton, Geoffrey. “The Appeal of PDP”. In Parallel Distributed Processing edited by Rumelhart, McClelland and the PDP Research Group, (1986), 503–529.Google Scholar

  • McCloskey, Michael. „Networks and Theories: The Place of Connectionism in Cognitive Science“ in Psychological Science, 2:6 (1991), 387–395.Google Scholar

  • McCulloch, Warren., Embodiments of Mind, Cambridge, Mass.: MIT Press, 1965.Google Scholar

  • McCulloch, Warren. and Pitts, Walter. „A logical calculus of the ideas immanent in nervous activity“. In Bulletin of Mathematical Biophysics, 5 (1943), 115–133.Google Scholar

  • McDonald, Cynthia and McDonald, Graham. (Eds.) Connectionism: Debates in Psychological Explanation, (2 vols.), Cambridge, Mass.: Blackwell Publishers, 1995.Google Scholar

  • Medler, David. “A Brief History of Connectionism” in Neural Computing Surveys, 1 (1998), 61–101.Google Scholar

  • Miller, Alexander, and Wright, Crispin. (Eds.), Rule-Following and Meaning, Ithaca, NY: McGill-Queen’s U. P., 2002.PubMedGoogle Scholar

  • Minsky, Marvin and Papert, Seymour. Perceptrons: An Introduction to Computational Geometry, Cambridge, Mass.: M.I.T. Press, 1969.Google Scholar

  • Mole, Christopher. “Dead Reckoning in the Desert Ant: A Defense of Connectionist Models”, in Review of Philosophy and Psychology, 5:2 (2014), 277–290.CrossrefGoogle Scholar

  • Mozer, Mike and Smolensky, Paul. „Using Relevance to Reduce Network Size Automatically“ in Connection Science, 1 (1989), 3–16.Google Scholar

  • Muller, Vincent. (Ed.) Fundamental Issues in Artificial Intelligence, New York, NY: Springer International, 2016.Google Scholar

  • Newell, Allen and Simon, Herbert. “Computer Science as Empirical Inquiry” in Communications of the ACM, 19:3 (1976), 113–126.Google Scholar

  • Newell Allen. “Physical Symbol Systems” Cognitive Science, 4 (1980), 135–183.CrossrefGoogle Scholar

  • Pitts, Walter and McCulloch, Warren. “How We Know Universals the Perception of Auditory and Visual Forms”, Bulletin of Mathematical Biophysics, 9:3 (1947), 127–147.CrossrefGoogle Scholar

  • Piccinini, Gualtiero. “The First Computational Theory of Mind and Brain: A Close Look at McCulloch and Pitts‘s‚ Logical Calculus of Ideas Immanent in Nervous Activity‘”, Synthese, 141:2 (2004), 175–215.Google Scholar

  • Plunkett, Kim and Elman, Jeffery. Exercises in Rethinking Innateness: A Handbook for Connectionist Simulations, Cambridge, Mass.: M.I.T. Press, 1997.Google Scholar

  • Pollack, Jordan. “Recursive Distributed Representations”, Artificial Intelligence, 46 (1990), 77–105.CrossrefGoogle Scholar

  • Pylyshyn, Zenon. Computation and Cognition: Towards a Foundation of Cognitive Science, Cambridge, Mass.: MIT Press, 1984.Google Scholar

  • Ramsey, William, Stitch, Stephen, and Rumelhart, David. (Eds.) Philosophy and Connectionist Theory, Hillsdale, NJ: Lawrence Erlbaum Associated, 1991.Google Scholar

  • Robinson, David. (1992), “Implications of Neural Networks for How We think about Brain Function”, in Behavioural and Brain Sciences, 15 (1992), 644–655.Google Scholar

  • Rosenblatt, Frank “The Perceptron: A Probabilistic Model For Information Storage and Organization in the Brain”, Psychological Review, 65:60 (1958), 386–408.Google Scholar

  • Rosenblatt, Frank. Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms, Washington, DC: Spartan books, 1962.Google Scholar

  • Rubio, Ezequiel (in press), “Computational Functionalism for the Deep Learning Era”, to appear in Minds and Machines.Google Scholar

  • Rumelhart, David, McClelland, Jay and the PDP Research Group, (1986), Parallel Distributed Processing: Explorations in the Microstructure of Cognition, M.I.T. Press, (Cambridge, MA), (2 vols).Google Scholar

  • Samet, Jerry, „The Historical Controversies Surrounding Innateness“, in The Stanford Encyclopedia of Philosophy Edward N. Zalta (Ed.), (2008) URL = <https://plato.stanford.edu/archives/fall2008/entries/innateness-history/>.

  • Schlatter, Mark and Aizawa, Ken. “Walter Pitts and „A Logical Calculus“”, Synthese, 162:2 (2008), 235–250.Google Scholar

  • Schneider, Walter. “Connectionism: Is it a Paradigm Shift for Psychology?” in Behavior Research Methods, Instruments & Computers, 19 (1987), 73–83.Google Scholar

  • Sejnowski, Terence. The Deep Learning Revolution, Cambridge, Mass.: M.I.T. Press, 2018.Google Scholar

  • Shea, N. “Representational Development Need Not Be Explicable-By-Content”, in Fundamental Issues in Artificial Intelligence, edited by Vincent Muller, (2016), 221–238.Google Scholar

  • Smolensky, Paul. “The Constituent Structure of Mental States: A Reply to Fodor and Pylyshyn” in Southern Journal of Philosophy, 26 (1987), 137–160.Google Scholar

  • Smolensky, Paul. “On the Proper Treatment of Connectionism” in Behavioural and Brain Sciences, 11 (1988), 1–74.CrossrefGoogle Scholar

  • Smolensky, Paul. “Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems” Artificial Intelligence, 46 (1990), 159–216.Google Scholar

  • Taddeo, Mariarosaria. and Floridi, Luciano. “The Debate on the Moral Responsibilities of Online Service Providers” in Science and Engineering Ethics, 22:6 (2016), 1575–1603.CrossrefGoogle Scholar

  • Thorndike, Edward. Fundamentals of Learning, New York, NY: Teachers College, Columbia University, 1932.Google Scholar

  • Van Gelder, Tim. “Compositionaility: A Connectionist Variant on a Classical Theme”, Cognitive Science, 14:3 (1990), 355–384.CrossrefGoogle Scholar

  • Vera, Alonso. and Simon, Herbert. “Reply to Touretzky and Pomerleau: Reconstructing Physical Symbol Systems”, Cognitive Science, 18 (1994), 355–360.CrossrefGoogle Scholar

  • Walker, Stephen. “A Brief History of Connectionism and Its Psychological Implications”, in Connectionism in Context (Human Centered Systems), edited by Clark and Lutz (1992), 123–144.Google Scholar

  • Waskan, Jonathon. “A Critique of Connectionist Semantics”, in Connection Science, 13(3) (2001), 277–292.Google Scholar

About the article

Received: 2019-04-29

Accepted: 2019-06-28

Published Online: 2019-08-12

Published in Print: 2019-01-01


Citation Information: Open Philosophy, Volume 2, Issue 1, Pages 190–205, ISSN (Online) 2543-8875, DOI: https://doi.org/10.1515/opphil-2019-0018.

Export Citation

© 2019 Istvan S. N. Berkeley, published by De Gruyter Open. This work is licensed under the Creative Commons Attribution 4.0 Public License. BY 4.0

Comments (0)

Please log in or register to comment.
Log in