Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

July 2007, Vol. 19, No. 7, Pages 1897-1918
(doi: 10.1162/neco.2007.19.7.1897)
© 2007 Massachusetts Institute of Technology
Combining Reconstruction and Discrimination with Class-Specific Sparse Coding
Article PDF (1.23 MB)
Abstract

Sparse coding is an important approach for the unsupervised learning of sensory features. In this contribution, we present two new methods that extend the traditional sparse coding approach with supervised components. Our goal is to increase the suitability of the learned features for classification tasks while keeping most of their general representation capability. We analyze the effect of the new methods using visualization on artificial data and discuss the results on two object test sets with regard to the properties of the found feature representation.