Matrix factorization is a family of linear-algebra methods that take a matrix and compute two or more matrices, when multiplied are equal to the input matrix
Kernels are fuctions that map points from a input space X to a feature space F where the non-linear patterns become linear
Kernel Matrix factorization is a similar method, however, instead of factorizing the input-space matrix, it factorizes a feature-space matrix.
To design, implement and evaluate a new KMF method that is able to compute an kernel-induced feature space factorization to a large-scale volume of data
The selected performance measure is the clustering accuracy, this measures the ratio between the number of correctly clustered instances and the total number of instances.
Linear kernel
Gaussian kernel