On-line learning for very large data sets

@inproceedings{Bottou2005OnlineLF,
  title={On-line learning for very large data sets},
  author={L{\'e}on Bottou and Yann le Cun},
  year={2005}
}
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… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 96 CITATIONS

Stochastic Learning

  • Advanced Lectures on Machine Learning
  • 2003
VIEW 12 EXCERPTS
CITES BACKGROUND

Efficient Methods For Large-Scale Empirical Risk Minimization

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Adaptive on-line optimizing the Gaussian kernel for classification based on the kernel target alignment

  • 2015 IEEE International Conference on Computer and Communications (ICCC)
  • 2015
VIEW 3 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

On Accelerated Gradient Approximation for Least Square Regression with L1-Regularization

  • 2015 IEEE Symposium Series on Computational Intelligence
  • 2015
VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2003
2020

CITATION STATISTICS

  • 6 Highly Influenced Citations

  • Averaged 8 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 12 REFERENCES

Statistical analysis of learning dynamics

  • Signal Processing
  • 1999
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Efficient Backprop

Y. Le Cun, L. Bottou, G. B. Orr, K.-R. Müller
  • Neural Networks , Tricks of the Trade , Lecture Notes in Computer Science 1524
  • 1998
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Experiments with a new

San Mateo, Y. CA. Morgan Kaufmann. Freund, R. E. Schapire
  • 1996

Comparison of classifier methods: a case study in handwritten digit recognition

  • Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5)
  • 1994
VIEW 1 EXCERPT

A Training Algor

Springer Verlag, Berlin, B. New York. Boser, I. Guyon, V. Vapnik
  • 1992