Learning sparse and deep representations : new algorithms and perspectives

@inproceedings{Newling2014LearningSA,
  title={Learning sparse and deep representations : new algorithms and perspectives},
  author={James Newling},
  year={2014}
}
Three papers related to representation learning are discussed. The first paper presents a broad overview of the field of unsupervised representation learning, the second paper presents a stochastic model for images, and the final paper presents a new approach to encoding images. The relationship between these papers is discussed, and a modification to the method of the third paper is proposed. 

Figures and Topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-8 OF 8 REFERENCES

Learning Feature Representations with K-Means

  • Neural Networks: Tricks of the Trade
  • 2012
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Representation Learning: A Review and New Perspectives

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2013
VIEW 2 EXCERPTS

An analysis of singlelayer networks in unsupervised feature learning

A. Coates, H. Lee, A. Ng
  • Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, ser. JMLR Workshop and Conference Proceedings, G. Gordon, D. Dunson, and M. Dudk, Eds., vol. 15. JMLR W&CP, 2011, pp. 215–223. [Online]. Available: http://jmlr.csail.mit.edu/proceedings/papers/v15/coate
  • 2011
VIEW 2 EXCERPTS

Similar Papers

Loading similar papers…