Kernel Networks with Fixed and Variable Widths

Abstrakt

The role of width in kernel models and radial-basis function networks is investigated with a special emphasis on the Gaussian case. Quantitative bounds are given on kernel-based regularization showing the effect of changing the width. These bounds are shown to be d-th powers of width ratios, and so they are exponential in the dimension of input data.

Kategorie a štítky

  • Konferenční příspěvek (mezinárodní konf.)