Learning Feature Representations with K-Means

@inproceedings{Coates2012LearningFR,
  title={Learning Feature Representations with K-Means},
  author={Adam Coates and Andrew Y. Ng},
  booktitle={Neural Networks: Tricks of the Trade},
  year={2012}
}
Many algorithms are available to learn deep hierarchies of features from unlabeled data, especially images. In many cases, these algorithms involve multi-layered networks of features (e.g., neural networks) that are sometimes tricky to train and tune and are difficult to scale up to many machines effectively. Recently, it has been found that K-means clustering can be used as a fast alternative training method. The main advantage of this approach is that it is very fast and easily implemented at… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-10 OF 272 CITATIONS, ESTIMATED 27% COVERAGE

FILTER CITATIONS BY YEAR

2012
2019

CITATION STATISTICS

  • 33 Highly Influenced Citations

  • Averaged 55 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 42 REFERENCES

An analysis of single-layer networks in unsupervised feature learning

  • A. Coates, H. Lee, A. Y. Ng
  • 14th International Conference on AI and…
  • 2011
Highly Influential
7 Excerpts

Similar Papers

Loading similar papers…