Search results with tag "Dimensionality reduction by learning an"

Dimensionality Reduction by Learning an Invariant Mapping

is not constrained by simple distance measures in the input space. The learning architecture is somewhat similar to the one discussed in [4, 5]. Section 2 describes the generalframework,the loss func-tion, and draws an analogy with a mechanical spring sys-tem. The ideas in this section are made concrete in sec-tion3.

  Reduction, Learning, Simple, Dimensionality, Dimensionality reduction by learning an