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

Neural Computation

August 15, 1998, Vol. 10, No. 6, Pages 1445-1454
(doi: 10.1162/089976698300017250)
© 1998 Massachusetts Institute of Technology
A Sparse Representation for Function Approximation
Article PDF (243.52 KB)
Tomaso Poggio
Center for Biological and Computational Learning and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A.
Federico Girosi
Center for Biological and Computational Learning and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, U.S.A.
Abstract

We derive a new general representation for a function as a linear combination of local correlation kernels at optimal sparse locations (and scales) and characterize its relation to principal component analysis, regularization, sparsity principles, and support vector machines.