mvpa2.kernels.sgΒΆ
PyMVPA shogun-based kernels
Provides interface to kernels defined in shogun toolbox. Commonly
used kernels are provided with convenience classes: LinearSGKernel,
RbfSGKernel, PolySGKernel. If you need to use some other shogun
kernel, use CustomSGKernel to define one.
Functions
exists(dep[, force, raise_, issueWarning, ...]) |
Test whether a known dependency is installed on the system. |
Classes
Bogus |
|
CustomSGKernel(kernel_cls[, kernel_params]) |
Class which can wrap any Shogun kernel and it’s kernel parameters |
Kernel(\*args, \*\*kwargs) |
Abstract class which calculates a kernel function between datasets |
LinearSGKernel([normalizer_cls, normalizer_args]) |
A basic linear kernel computed via Shogun: K(a,b) = a*b.T |
Parameter(default[, constraints, ro, index, ...]) |
This class shall serve as a representation of a parameter. |
PolySGKernel(\*\*kwargs) |
Polynomial kernel: K(a,b) = (a*b.T + c)**degree |
PrecomputedSGKernel([matrix]) |
A kernel which is precomputed from a numpy array or a Shogun kernel |
RbfSGKernel(\*\*kwargs) |
Radial basis function: K(a,b) = exp(-||a-b||**2/sigma) |
SGKernel(\*args, \*\*kwargs) |
A Kernel object with internal representation in Shogun |
