Spectral clustering is a meta-algorithm, meaning that there are dozens of variations. The demo implementation uses a radial basis function (RBF) kernel to construct the affinity matrix, a normalized ...

Two unsupervised spectral feature selection algorithms are proposed in this paper. They group features using advanced Self-Tuning spectral clustering algorithm based on local standard deviation ...

The demo displays the first five rows and five columns of two of the key matrices that are computed by the spectral clustering algorithm. The 18-by-18 affinity matrix holds values that are measures of ...