Kernels

Methods:

.matrix(x)

Return the kernel matrix K_{ij} = k(x_i, x_j).

.vector(a, x)

Return the kernel vector K_i = k(x_i, a).

Linear Kernel

class mlpy.KernelLinear

Linear Kernel

K(x, x') = x \cdot x'

Gaussian Kernel

class mlpy.KernelGaussian(sigma)

Gaussian Kernel

K(x, x') = e^{-\frac{\|x - x'\|}{2 \sigma^2}}

Polynomial Kernel

class mlpy.KernelPolynomial(d)

Polynomial Kernel

K(x, x') = {(x \cdot x' + 1)}^d