Hostname: page-component-586b7cd67f-tf8b9 Total loading time: 0 Render date: 2024-11-30T21:17:24.390Z Has data issue: false hasContentIssue false
  • English
  • Français

To Transform the Phenomena: Feyerabend, Proliferation, and Recurrent Neural Networks

Published online by Cambridge University Press:  01 April 2022

Paul M. Churchland
Paul M. Churchland*
Affiliation:
University of California, San Diego
*
†Department of Philosophy-0302, University of California at San Diego, La Jolla, CA 92093.
Get access Rights & Permissions [Opens in a new window]

Abstract

Paul Feyerabend recommended the methodological policy of proliferating competing theories as a means to uncovering new empirical data, and thus as a means to increase the empirical constraints that all theories must confront. Feyerabend's policy is here defended as a clear consequence of connectionist models of explanatory understanding and learning. An earlier connectionist “vindication” is criticized, and a more realistic and penetrating account is offered in terms of the computationally plastic cognitive profile displayed by neural networks with a recurrent architecture.

Type
Symposium: Paul Feyerabend and His Legacy
Information
Philosophy of Science , Volume 64 , Issue S4: Supplement. Proceedings of the 1996 Biennial Meetings of the Philosophy of Science Association. Part II: Symposia Papers Dec., 1997 , 1997 , pp. S408 - S420
Copyright
Copyright © Philosophy of Science Association 1997

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Footnotes

‡

My thanks, for several helpful suggestions, to two anonymous referees.

References

Churchland, P.M. (1989a), “Learning and Conceptual Change”, Ch. 11 of A Neurocomputational Perspective: The Nature of Mind and the Structure of Science. Cambridge, MA: MIT Press, pp. 231–253.Google Scholar
Churchland, P.M. (1989b), “On the Nature of Explanation: A PDP Approach,” Ch. 10 of A Neurocomputational Perspective: The Nature of Mind and the Structure of Science. Cambridge, MA: MIT Press, pp. 197–230. Reprinted in J. Misiek (ed.) (1994), The Problem of Rationality in Science and Its Philosophy. Boston Studies in the Philosophy of Science, v. 175. Dordrecht: Kluwer, pp. 81–114.Google Scholar
Churchland, P.M. (1992), “A Deeper Unity: Some Feyerabendian Themes in Neurocomputational Form”, in Giere, R. (ed.), Cognitive Models of Science. Minnesota Studies in the Philosophy of Science, v. 15. Minneapolis: University of Minnesota Press, pp. 341–363.Google Scholar
Feyerabend, P. K. (1958), “An Attempt at a Realistic Interpretation of Experience”, Proceedings of the Aristotelian Society 58: 143–170. Reprinted in P. K. Feyerabend (1981), Realism, Rationalism, and Scientific Method: Philosophical Papers, v. 1. Cambridge: Cambridge University Press, pp. 17–43.CrossRefGoogle Scholar
Feyerabend, P. K. (1962), “Explanation, Reduction, and Empiricism”, in H. Feigl and G. Maxwell (eds.), Scientific Explanation, Space and Time. Minnesota Studies in the Philosophy of Science, v. 3. Minneapolis: University of Minnesota Press, 28–97.Google Scholar
Feyerabend, P. K. (1963), “How to be a Good Empiricist—A Plea for Tolerance in Matters Epistemological”, in Baumrin, B. (ed.), Philosophy of Science: The Delaware Seminar, v. 2. New York, NY: Interscience Publications, pp. 3–19. Reprinted in B. Brody (ed.) (1970), Readings in the Philosophy of Science. Englewood Cliffs, NJ: Prentice Hall, pp. 319–342. Also reprinted in H. Morick (ed.) (1972), Challenges to Empiricism. Belmont, CA: Wadsworth, pp. 164–193.Google Scholar