ptypy.engines.ML.GaussianModel#

class ptypy.engines.ML.GaussianModel(MLengine)#

Gaussian noise model. TODO: feed actual statistical weights instead of using the Poisson statistic heuristic.

__init__(MLengine)#: Core functions for ML computation using a Gaussian model.

Methods

`__init__`(MLengine)	Core functions for ML computation using a Gaussian model.
`new_grad`()	Compute a new gradient direction according to a Gaussian noise model.
`poly_line_all_coeffs`(ob_h, pr_h)	Compute all the coefficients of the polynomial for line minimization in direction h
`poly_line_coeffs`(ob_h, pr_h)	Compute the coefficients of the polynomial for line minimization in direction h
`prepare`()

new_grad()#

Compute a new gradient direction according to a Gaussian noise model.

Note: The negative log-likelihood and local errors are also computed here.

poly_line_all_coeffs(ob_h, pr_h)#: Compute all the coefficients of the polynomial for line minimization in direction h

poly_line_coeffs(ob_h, pr_h)#: Compute the coefficients of the polynomial for line minimization in direction h