Go to the source code of this file.
Namespaces | |
| viennacl | |
| Main namespace in ViennaCL. Holds all the basic types such as vector, matrix, etc. and defines operations upon them. | |
| viennacl::linalg | |
| Provides all linear algebra operations which are not covered by operator overloads. | |
| viennacl::linalg::cuda | |
| Holds all CUDA compute kernels used by ViennaCL. | |
Functions | |
| template<typename NumericT > | |
| __global__ void | viennacl::linalg::cuda::el_wise_mul_div (NumericT *matrix1, NumericT const *matrix2, NumericT const *matrix3, unsigned int size) |
| Main CUDA kernel for nonnegative matrix factorization of a dense matrices. More... | |
| template<typename NumericT > | |
| void | viennacl::linalg::cuda::nmf (viennacl::matrix_base< NumericT > const &V, viennacl::matrix_base< NumericT > &W, viennacl::matrix_base< NumericT > &H, viennacl::linalg::nmf_config const &conf) |
| The nonnegative matrix factorization (approximation) algorithm as suggested by Lee and Seung. Factorizes a matrix V with nonnegative entries into matrices W and H such that ||V - W*H|| is minimized. More... | |