ML Anthology

A Sparse Representation for Function Approximation

Tomaso A. Poggio, Federico Girosi
NeCo 1998 pp. 1445-1454
doi:10.1162/089976698300017250 /neco/1998/poggio1998neco-sparse/

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.

NeCo Semantic Scholar

Cite

Text

Poggio and Girosi. "A Sparse Representation for Function Approximation." Neural Computation, 1998. doi:10.1162/089976698300017250

Markdown

[Poggio and Girosi. "A Sparse Representation for Function Approximation." Neural Computation, 1998.](https://mlanthology.org/neco/1998/poggio1998neco-sparse/) doi:10.1162/089976698300017250

BibTeX

@article{poggio1998neco-sparse,
  title     = {{A Sparse Representation for Function Approximation}},
  author    = {Poggio, Tomaso A. and Girosi, Federico},
  journal   = {Neural Computation},
  year      = {1998},
  pages     = {1445-1454},
  doi       = {10.1162/089976698300017250},
  volume    = {10},
  url       = {https://mlanthology.org/neco/1998/poggio1998neco-sparse/}
}