Learning Fast Approximations of Sparse Coding

  title={Learning Fast Approximations of Sparse Coding},
  author={Karol Gregor and Yann LeCun},
In Sparse Coding (SC), input vectors are reconstructed using a sparse linear combination of basis vectors. SC has become a popular method for extracting features from data. For a given input, SC minimizes a quadratic reconstruction error with an L1 penalty term on the code. The process is often too slow for applications such as real-time pattern recognition. We proposed two versions of a very fast algorithm that produces approximate estimates of the sparse code that can be used to compute good… CONTINUE READING
Highly Influential
This paper has highly influenced 55 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 652 citations. REVIEW CITATIONS

7 Figures & Tables



Citations per Year

653 Citations

Semantic Scholar estimates that this publication has 653 citations based on the available data.

See our FAQ for additional information.