Sparse Feature Learning for Deep Belief Networks

  title={Sparse Feature Learning for Deep Belief Networks},
  author={Marc'Aurelio Ranzato and Y-Lan Boureau and Yann LeCun},
Unsupervised learning algorithms aim to discover the struc ture hidden in the data, and to learn representations that are more suitable as input to a supervised machine than the raw input. Many unsupervised methods are based on re c structing the input from the representation, while constraining the repr esentation to have certain desirable properties (e.g… CONTINUE READING

1 Figure or Table



Citations per Year

693 Citations

Semantic Scholar estimates that this publication has 693 citations based on the available data.

See our FAQ for additional information.