rcognita.models.ModelGaussianConditional

class rcognita.models.ModelGaussianConditional(expectation_function=None, arg_condition=None, weights=None, jitter=1e-06)

Gaussian probability distribution model with weights[0] being an expectation vector and weights[1] being a covariance matrix. The expectation vector can optionally be generated

__init__(expectation_function=None, arg_condition=None, weights=None, jitter=1e-06)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__([expectation_function, …])	Initialize self.
cache_weights([weights])
compute_gradient(argin)
forward(*args[, weights])
restore_weights()	Assign the weights of the cached model to the active model.
sample_from_distribution(argin)
update(new_weights)
update_and_cache_weights(weights)
update_covariance()
update_expectation(arg_condition)
update_weights(weights)

Attributes

model_name