Premium
On‐line learning for very large data sets
Author(s) -
Bottou Léon,
Le Cun Yann
Publication year - 2005
Publication title -
applied stochastic models in business and industry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.413
H-Index - 40
eISSN - 1526-4025
pISSN - 1524-1904
DOI - 10.1002/asmb.538
Subject(s) - computer science , artificial intelligence , convergence (economics) , machine learning , line (geometry) , online machine learning , scale (ratio) , algorithm , unsupervised learning , mathematics , physics , geometry , quantum mechanics , economics , economic growth
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.