Long Random Linear Programs Do Not Generalize

Author: Langdon, W.B.

Source: Genetic Programming and Evolvable Machines, Volume 2, Number 2, June 2001 , pp. 95-100(6)

Publisher: Springer

Buy & download fulltext article:

OR

Price: $47.00 plus tax (Refund Policy)

Abstract:

The chance of solving a problem by random search of long linear programs tends to a limit as their size increases. When all outputs are equally used this limit is no more than 2^−|test set|. The chance of randomly finding a long linear general solution is exponentially small.

Keywords: generality; genetic programming; random search

Document Type: Regular Paper

Affiliations: Computer Science, University College, London, Gower Street, London, WC1E 6BT, UK w.langdon@cs.ucl.ac.uk

Publication date: June 1, 2001

Related content

Key

Free Content
Free content
New Content
New content
Open Access Content
Open access content
Subscribed Content
Subscribed content
Free Trial Content
Free trial content

Text size:

A | A | A | A
Share this item with others: These icons link to social bookmarking sites where readers can share and discover new web pages. print icon Print this page