Article contents
Is the learning paradox resolved?
Published online by Cambridge University Press: 01 December 1997
Abstract
We argue that on logical grounds the constructivist algorithms mentioned by Quartz & Sejnowski (Q&S) do not resolve the learning paradox. In contrast, a neural network might acquire a more powerful structure by means of phase transitions. The latter kind of developmental mechanism can be in agreement with the constructivist manifesto.
- Type
- Open Peer Commentary
- Information
- Copyright
- © 1997 Cambridge University Press
- 4
- Cited by