A Neural Support Vector Network architecture with adaptive kernels

17 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Predicting Parameters in Deep Learning (2013, background): “Using different types of kernels to encode different types of prior knowledge on the weight space, or even learning the kernel functions directly as part of the optimization procedure as in [27] are possibilities that deserve exploration.”
Learning a similarity metric discriminatively, with application to face verification (2005, background): “Among other things, they can be used to build invariant kernel functions with which to build Support Vector Machines and other kernelbased models [17].”