Trading Spaces: Connectionism and the Limits of Uninformed Learning


It is widely appreciated that the difficulty of a particluar computation varies according to how the input data are presented. What is less understood is the effect of this computation/representation tradeoff within familiar learning paradigms. We argue that existing learning algoritms are often poorly equipped to solve problems involving a certain type of important and widespread regularity, which we call 'type-2' regularity. The solution in these cases is to trade achieved representation against computational search. We investigate several ways in which such a trade-off may be pursued including simple incremental learning, modular connectionism, and the developmental hypothesis of 'representational redescription'. In addition, the most distinctive features of human cognition- language and culture- may themselves be viewed as adaptions enabling this representation/computation trade-off to be pursued on an even grander scale.



    Upload a copy of this work     Papers currently archived: 93,031

External links

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

Through your library

  • Only published works are available at libraries.


Added to PP

49 (#333,799)

6 months
4 (#863,607)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Andy Clark
University of Sussex

Citations of this work

Word and Action: Reconciling Rules and Know-How in Moral Cognition.Andy Clark - 2000 - Canadian Journal of Philosophy 30 (sup1):267-289.
How to do things without words.D. Spurrett & S. J. Cowley - 2004 - Language Sciences 26 (5):443-466.

Add more citations

References found in this work

No references found.

Add more references