pyjuice.nodes.distributions.Gaussian

class pyjuice.nodes.distributions.Gaussian(mu: float | None = None, sigma: float | None = None, min_sigma: float = 0.01)

A class representing Gaussian distributions.

Note:

mu and sigma are used to specify (approximately) the mean and std of the data. This is used for parameter initialization.

Note:

The parameters will NOT be initialized directly using the values of mu and sigma, perturbations will be added. You can specify the initialization behavior by passing perturbation, mu, and sigma to the init_parameters function.

Parameters:

  • mu (float) – mean of the Gaussian

  • sigma (float) – standard deviation of the Gaussian

__init__(mu: float | None = None, sigma: float | None = None, min_sigma: float = 0.01)

Methods

num_param_flows()

The number of parameter flows per node.

num_parameters()

The number of parameters per node.

Attributes

need_meta_parameters

A flag indicating whether users need to pass in meta-parameters to the constructor of InputNodes.