To Transform the Phenomena
Feyerabend, Proliferation, and Recurrent Neural Networks
Bibliographic Data
| ID | 10706705 |
|---|---|
| Authors | Paul M Churchland (University of California San Diego, corresponding author) |
| Year | 1997 |
| Volume | 64 |
| Issue | S4 |
| Pages | S408-S420 |
| Publication date | 1997-01-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Philosophy of Science (JOURNAL) |
| Journal identifiers | ISSN: 0031-8248 • E-ISSN: 1539-767X |
| Publisher | Cambridge University Press (CUP) (PUBLISHER) |
| DOI | 10.1086/392618 |
| OpenAlex | W2011181205 |
| Language | EN |
| Citations received | 2 |
| References cited | 2 |
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
Artificial neural network · Cognition · Cognitive science · Connectionism · Machine learning · Recurrent neural network · Artificial Intelligence · Complex Systems and Time Series Analysis · Computational and Text Analysis Methods · Computer Science · Neuroscience · Philosophy and History of Science · Psychology
| Unique citing works | 2 |
|---|---|
| Citations per year | 0.1 |
| Citation span | 2005 - 2016 (12) |
| Citation velocity | historical |
| Highly cited | No |
| Citation types | Neutral: 1 |