norse.torch.functional.gaussian_rbf#

norse.torch.functional.gaussian_rbf(tensor: Tensor, sigma: float = 1)[source]#

A gaussian radial basis kernel that calculates the radial basis given a distance value (distance between $x$ and a data value $x^{\prime }$, or $\Vert \mathbf{x}-{\mathbf{x}}^{\prime }{\Vert }^2$ below).

$$K(\mathbf{x},{\mathbf{x}}^{\prime })=\exp (-\frac{\Vert \mathbf{x}-{\mathbf{x}}^{\prime }{\Vert }^2}{2{\sigma }^2})$$

Parameters:

tensor (torch.Tensor): The tensor containing distance values to convert to radial bases sigma (float): The spread of the gaussian distribution. Defaults to 1.