To transform the phenomena: Feyerabend, proliferation, and recurrent neural networks
Philosophy of Science 64 (4):420 (1997)
| 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 | |||||||||
| 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: 5,865 |
| External links |
 |
| Through your library | Configure |
Similar books and articlesDan Lloyd (1996). Consciousness, Connectionism, and Cognitive Neuroscience: A Meeting of the Minds. Philosophical Psychology 9 (1):61-78.
Harvey Siegel (1989). Farewell to Feyerabend. Inquiry 32 (3):343 – 369.
Enrico Blanzieri (1997). Dynamical Learning Algorithms for Neural Networks and Neural Constructivism. Behavioral and Brain Sciences 20 (4):559-559.
Dan Hunter (1999). Out of Their Minds: Legal Theory in Neural Networks. Artificial Intelligence and Law 7 (2-3).
Gualtiero Piccinini (2008). Some Neural Networks Compute, Others Don't. Neural Networks 21 (2-3):311-321.
Paul Skokowski (2007). Networks with Attitudes. Artificial Intelligence and Society 22 (3):461-470.
Analytics
Monthly downloads |
Added to index2009-01-28Total downloads22 ( #57,056 of 556,807 )Recent downloads (6 months)1 ( #64,847 of 556,807 )How can I increase my downloads? |
My notes
Discussion
