On‐line learning for very large data sets

Léon Bottou and Yann Le Cun

Applied Stochastic Models in Business and Industry, 2005, vol. 21, issue 2, 137-151

Abstract: The design of very large learning systems presents many unsolved challenges. Consider, for instance, a system that ‘watches’ television for a few weeks and learns to enumerate the objects present in these images. Most current learning algorithms do not scale well enough to handle such massive quantities of data. Experience suggests that the stochastic learning algorithms are best suited to such tasks. This is at first surprising because stochastic learning algorithms optimize the training error rather slowly. Our paper reconsiders the convergence speed in terms of how fast a learning algorithm optimizes the testing error. This reformulation shows the superiority of the well designed stochastic learning algorithm. Copyright © 2005 John Wiley & Sons, Ltd.

Date: 2005
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://doi.org/10.1002/asmb.538

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wly:apsmbi:v:21:y:2005:i:2:p:137-151

Access Statistics for this article

More articles in Applied Stochastic Models in Business and Industry from John Wiley & Sons
Bibliographic data for series maintained by Wiley Content Delivery ().