David Bourget (Western Ontario)
David Chalmers (ANU, NYU)
Rafael De Clercq
Jack Alan Reynolds
Learn more about PhilPapers
Philosophical Psychology 13 (1):47-76 (2000)
If connectionism is to be an adequate theory of mind, we must have a theory of representation for neural networks that allows for individual differences in weighting and architecture while preserving sameness, or at least similarity, of content. In this paper we propose a procedure for measuring sameness of content of neural representations. We argue that the correct way to compare neural representations is through analysis of the distances between neural activations, and we present a method for doing so. We then use the technique to demonstrate empirically that different artificial neural networks trained by backpropagation on the same categorization task, even with different representational encodings of the input patterns and different numbers of hidden units, reach states in which representations at the hidden units are similar. We discuss how this work provides a rebuttal to Fodor and Lepore's critique of Paul Churchland's state space semantics.
|Keywords||Metaphysics Mind Neural Representation Science Churchland, P Putnam, H|
|Categories||categorize this paper)|
Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
|Through your library|
References found in this work BETA
No references found.
Citations of this work BETA
Christopher Gauker (2007). A Critique of the Similarity Space Theory of Concepts. Mind and Language 22 (4):317–345.
Nicholas Shea (2007). Content and Its Vehicles in Connectionist Systems. Mind and Language 22 (3):246–269.
Timothy Schroeder (2007). A Recipe for Concept Similarity. Mind and Language 22 (1):68-91.
Nancy Salay (2008). Thinking Without Global Generalisations: A Cognitive Defence of Moral Particularism. Inquiry 51 (4):390 – 411.
Eliano Pessa & Graziano Terenzi (2007). Semiosis in Cognitive Systems: A Neural Approach to the Problem of Meaning. [REVIEW] Mind and Society 6 (2):189-209.
Similar books and articles
Alex Vereschagin, Mike Collins & Pete Mandik (2007). Evolving Artificial Minds and Brains. In Drew Khlentzos & Andrea Schalley (eds.), Mental States Volume 1: Evolution, function, nature. John Benjamins.
Andy Clark & M. Wheeler (1999). Genie Representation: Reconciling Content and Causal Complexity. British Journal for the Philosophy of Science 50 (1):103 - 135.
Dan Hunter (1999). Out of Their Minds: Legal Theory in Neural Networks. [REVIEW] Artificial Intelligence and Law 7 (2-3):129-151.
Stuart R. Hameroff (1998). More Neural Than Thou (Reply to Churchland). In S. Ameroff, Alfred W. Kaszniak & A. C. Scott (eds.), Toward a Science of Consciousness Ii: The 1996 Tucson Discussions and Debates. Mit Press.
Paul M. Churchland (1998). Conceptual Similarity Across Sensory and Neural Diversity: The Fodor/Lepore Challenge Answered. Journal of Philosophy 95 (1):5-32.
Francisco Calvo Garzón (2000). State Space Semantics and Conceptual Similarity: Reply to Churchland. Philosophical Psychology 13 (1):77-95.
Gualtiero Piccinini (2008). Some Neural Networks Compute, Others Don't. Neural Networks 21 (2-3):311-321.
Pete Mandik (2003). Varieties of Representation in Evolved and Embodied Neural Networks. Biology and Philosophy 18 (1):95-130.
Patricia S. Churchland & Terrence J. Sejnowski (1989). Neural Representation and Neural Computation. In L. Nadel (ed.), Philosophical Perspectives. MIT Press. 343-382.
Added to index2009-01-28
Total downloads54 ( #36,265 of 1,681,726 )
Recent downloads (6 months)4 ( #60,287 of 1,681,726 )
How can I increase my downloads?