Regularization Theory and Neural Networks Architectures

@article{citeulike:2896182, abstract = {We had previously shown that regularization principles lead to approximation schemes which are equivalent to networks with one layer of hidden units, called Regularization Networks. In particular, standard smoothness functionals lead to a subclass of regularization networks, the well known Radial Basis Functions approximation schemes. This paper shows that regularization networks encompass a much broader range of approximation schemes, including many of the popular general additive models and...}, author = {Girosi, Federico and Jones, Michael and Poggio, Tomaso }, citeulike-article-id = {2896182}, journal = {Neural Computation}, keywords = {kernel}, number = {2}, pages = {219--269}, posted-at = {2008-06-15 14:14:05}, priority = {0}, title = {Regularization Theory and Neural Networks Architectures}, url = {http://citeseer.ist.psu.edu/girosi95regularization.html}, volume = {7}, year = {1995} }

TY - JOUR ID - citeulike:2896182 L3 - citeulike-article-id:2896182 TI - Regularization Theory and Neural Networks Architectures JF - Neural Computation VL - 7 IS - 2 SP - 219 EP - 269 N2 - We had previously shown that regularization principles lead to approximation schemes which are equivalent to networks with one layer of hidden units, called Regularization Networks. In particular, standard smoothness functionals lead to a subclass of regularization networks, the well known Radial Basis Functions approximation schemes. This paper shows that regularization networks encompass a much broader range of approximation schemes, including many of the popular general additive models and... KW - kernel AU - Girosi, Federico AU - Jones, Michael AU - Poggio, Tomaso PY - 1995/// UR - http://citeseer.ist.psu.edu/girosi95regularization.html ER -