Is the learning paradox resolved?

Behavioral and Brain Sciences 20 (4):573-574 (1997)
  Copy   BIBTEX

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.

Other Versions

No versions found

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 101,060

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Irresistible environment meets immovable neurons.Jeffrey Foss - 1997 - Behavioral and Brain Sciences 20 (4):565-566.
Neural constructivism: How mammals make modules.Robert A. Barton - 1997 - Behavioral and Brain Sciences 20 (4):556-557.

Analytics

Added to PP
2009-01-28

Downloads
30 (#747,543)

6 months
11 (#337,502)

Historical graph of downloads
How can I increase my downloads?