Moving the goal posts: A reply to Dawson and Piercey
Minds and Machines 16 (4):471-478 (2006)
| Abstract | Berkeley [Minds Machines 10 (2000) 1] described a methodology that showed the subsymbolic nature of an artificial neural network system that had been trained on a logic problem, originally described by Bechtel and Abrahamsen [Connectionism and the mind. Blackwells, Cambridge, MA, 1991]. It was also claimed in the conclusion of this paper that the evidence was suggestive that the network might, in fact, count as a symbolic system. Dawson and Piercey [Minds Machines 11 (2001) 197] took issue with this latter claim. They described some lesioning studies that they argued showed that Berkeley’s (2000) conclusions were premature. In this paper, these lesioning studies are replicated and it is shown that the effects that Dawson and Piercey rely upon for their argument are merely an artifact of a threshold function they chose to employ. When a threshold function much closer to that deployed in the original studies is used, the significant effects disappear. | |||||||||
| Keywords | No keywords specified (fix it) | |||||||||
| Categories | ||||||||||
| Options |
|
|||||||||
Download options| PhilPapers Archive |
Upload a copy of this paper Check publisher's policy on self-archival Papers currently archived: 5,705 |
| External links |
  Try with proxy. |
| Through your library | Configure |
Similar books and articlesRobert Piercey (2004). Hegel, Novelty, and Philosophical Novelty. International Studies in Philosophy 36 (1):143-159.
Angus Dawson (ed.) (2011). Public Health Ethics: Key Concepts and Issues in Policy and Practice. Cambridge University Press.
Robert Piercey (2005). Gadamer on the Relation Between Philosophy and Its History. Idealistic Studies 35 (1):21-33.
Michael R. W. Dawson & C. Darren Piercey (1999). Better Theories Are Needed to Distinguish Perception From Cognition. Behavioral and Brain Sciences 22 (3):374-375.
Lawrence A. Shapiro (2000). Michael R. W. Dawson, Understanding Cognitive Science. Minds and Machines 10 (3):440-444.
M. R. W. Dawson, D. A. Medler, D. B. McCaughan, L. Willson & M. Carbonaro (2000). Using Extra Output Learning to Insert a Symbolic Theory Into a Connectionist Network. Minds and Machines 10 (2):171-201.
Michael R. W. Dawson, D. A. Medler & Istvan S. N. Berkeley (1997). PDP Networks Can Provide Models That Are Not Mere Implementations of Classical Theories. Philosophical Psychology 10 (1):25-40.
Robert Piercey (2009). The Uses of the Past From Heidegger to Rorty: Doing Philosophy Historically. Cambridge University Press.
Istvan S. N. Berkeley (2000). What the #$*%! Is a Subsymbol? Minds and Machines 10 (1):1-13.
Analytics
Monthly downloads |
Added to index2009-01-28Total downloads15 ( #78,732 of 549,196 )Recent downloads (6 months)1 ( #63,397 of 549,196 )How can I increase my downloads? |
My notes
Discussion
