rnx_auc_embed | R Documentation |
The RNX curve is formed by calculating the rnx_crm
metric for
different sizes of neighborhood. Each value of RNX is scaled according to
the natural log of the neighborhood size, to give a higher weight to smaller
neighborhoods. An AUC of 1 indicates perfect neighborhood preservation, an
AUC of 0 is due to random results.
rnx_auc_embed(din, dout)
din |
Input distance matrix. |
dout |
Output distance matrix. |
Area under the RNX curve.
Lee, J. A., Peluffo-Ordo'nez, D. H., & Verleysen, M. (2015). Multi-scale similarities in stochastic neighbour embedding: Reducing dimensionality while preserving both local and global structure. Neurocomputing, 169, 246-261.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.