MultiGaussian#

class sinabs.activation.MultiGaussian(mu: float = 0.0, sigma: float = 0.5, h: float = 0.15, s: float = 6, grad_scale: float = 1.0)[source]#

Surrogate gradient as defined in Yin et al., 2021.

https://www.biorxiv.org/content/10.1101/2021.03.22.436372v2

Parameters

mu: The mean of the Gaussian. sigma: The standard deviation of the Gaussian. h: Controls the magnitude of the negative parts of the kernel. s: Controls the width of the negative parts of the kernel. grad_scale: Scale the gradients arbitrarily.

Parameters
  • mu (float) –

  • sigma (float) –

  • h (float) –

  • s (float) –

  • grad_scale (float) –

Return type

None