modules.applications.qml.generative_modeling.generative_modeling.GenerativeModeling

class GenerativeModeling

Bases: QML

Generative models enable the creation of new data by learning the underlying probability distribution of the training data set of interest. More specifically, a generative model attempts to learn an unknown probability distribution Q by modeling an approximated probability distribution P(θ) which is parameterized by a set of variables θ. Data sampled from Q is used to train a model by tuning θ such that P(θ) more closely approximates Q.

__init__(): Constructor method.

Methods

`__init__`()	Constructor method.
`generate_problem`(config)	The number of qubits is chosen for this problem.
`get_application`()	Gets the application.
`get_available_submodule_options`()	Gets the list of available options.
`get_available_submodules`(option)	If the module has submodules depending on certain options, this method should adjust the submodule_options accordingly.
`get_default_submodule`(option)	Returns the default submodule based on the given option.
`get_depending_parameters`(option, config)	If the module has parameters depending on certain options, this method should return the parameters for the given option.
`get_parameter_options`()	Returns the configurable settings for this application.
`get_requirements`()	Returns requirements of this module.
`get_solution_quality_unit`()
`get_submodule`(option)	Submodule is instantiated according to the information given in self.sub_options.
`postprocess`(input_data, config, **kwargs)	Process the solution here, then validate and evaluate it.
`preprocess`(input_data, config, **kwargs)	Generate the actual problem instance in the preprocess function.
`save`(path, iter_count)	Placeholder method for saving output to a file.

generate_problem(config: dict) → dict

The number of qubits is chosen for this problem.

Parameters:: config -- Dictionary including the number of qubits
Returns:: Dictionary with the number of qubits

get_application() → any

Gets the application.

Returns:: self.application

get_available_submodule_options() → list

Gets the list of available options.

Returns:: List of module options

get_available_submodules(option: list) → list

If the module has submodules depending on certain options, this method should adjust the submodule_options accordingly.

Parameters:: option -- List of chosen options
Returns:: List of available submodules

get_default_submodule(option: str) → ContinuousData | DiscreteData

Returns the default submodule based on the given option.

Parameters:: option -- The submodule option to select
Returns:: Instance of the selected submodule
Raises:: NotImplemented -- If the provided option is not implemented

get_depending_parameters(option: str, config: dict) → dict

If the module has parameters depending on certain options, this method should return the parameters for the given option.

Parameters:

option -- The chosen option
config -- Current config dictionary

Returns:

The parameters for the given option

get_parameter_options() → dict

Returns the configurable settings for this application.

Returns:: Dictionary of configurable parameters

return {
        "n_qubits": {
            "values": [4, 6, 8, 10, 12],
            "description": "How many qubits do you want to use?"
        }
    }

static get_requirements() → list[dict]

Returns requirements of this module.

Returns:: List of dicts with requirements of this module

get_submodule(option: str) → Core

Submodule is instantiated according to the information given in self.sub_options. If self.sub_options is None, get_default_submodule is called as a fallback.

Parameters:: option -- String with the options
Returns:: Instance of a module

postprocess(input_data: dict, config: dict, **kwargs: dict) → tuple[dict, float]

Process the solution here, then validate and evaluate it.

Parameters:

input_data -- A representation of the quantum machine learning model that will be trained
config -- Config specifying the parameters of the training
kwargs -- Optional keyword arguments

Returns:

Tuple with input_data and the function's computation time

preprocess(input_data: dict, config: dict, **kwargs: dict) → tuple[dict, float]

Generate the actual problem instance in the preprocess function.

Parameters:

input_data -- Usually not used for this method
config -- Config for the problem creation
kwargs -- Optional additional arguments

Returns:

Tuple containing qubit number and the function's computation time

save(path: str, iter_count: int) → None

Placeholder method for saving output to a file.

Parameters:

path -- Path to save the file
iter_count -- Iteration count