training: The package containing functionalities needed for model training#
This part of the package contains functions that are needed for model training.
likelihood_cmhn#
This submodule contains functions to work with the transition rate matrix Q in a restricted state-space as well as functions to compute the marginal log-likelihood score and its gradient making use of state-space restriction.
likelihood_omhn#
This submodule contains functions that can be used to compute the scores and gradients for the oMHN.
penalties_cmhn#
This module contains penalties used during training for regularization.
penalties_omhn#
This module contains penalties used during training for regularization.
state_containers#
This submodule contains functions and classes to store and convert mutation states used for training. It also contains a function to compute an independence model that can be used as a starting point for training a new MHN.
regularized_optimization#
This submodule contains functions to learn an MHN.