squlearn.encoding_circuit.RandomLayeredEncodingCircuit

class squlearn.encoding_circuit.RandomLayeredEncodingCircuit(num_qubits: int, num_features: int, seed: int = 0, min_num_layers: int = 2, max_num_layers: int = 10, feature_probability=0.3)

Creates a random Layered encoding circuit with no trainable parameters.

A random Layered encoding circuit is generated by randomly selecting gates from a predefined action space. The action space contains single qubit gates, two qubit gates. Non-parametrized gates that are placed in the random circuit are: H, X, Y, Z, cx, cy, cz. Included paramererized gates are Rx, Ry, Rz, crx, cry, crz, where the parameter is either a fixed angle or a feature. Fixed angles are \(\pi\), \(\pi/2\), \(\pi/3\), \(\pi/4\), \(\pi/8\). Feature \(x\) are encoded as \(x\), \(x\pi\), \(\arctan(x)\). The random circuit generation enforces, that all features are encoded at least once.

A seed is used to identify the random circuit, so that the same circuit can be reproduced. The number of layers is randomly chosen between min_num_layers and max_num_layers. The probability of a layer containing an encoding gate is given by feature_probability.

Example for 4 qubits and a 6 dimensional feature vector

(Source code, png, hires.png, pdf)

Parameters:

• num_qubits (int) – Number of qubits of the encoding circuit

• num_features (int) – Dimension of the feature vector

• seed (int) – Seed for the random number generator (default: 0)

• min_num_layers (int) – Minimum number of layers (default: 2)

• max_num_layers (int) – Maximum number of layers (default: 10)

• feature_probability (float) – Probability of a layer containing an encoding gate (default: 0.3)

draw(output: str = None, feature_label: str = 'x', parameter_label: str = 'p', decompose: bool = False, **kwargs) → None

Draws the encoding circuit circuit using the QuantumCircuit.draw() function.

Parameters:

• feature_label (str) – Label for the feature vector (default:”x”).

• parameter_label (str) – Label for the parameter vector (default:”p”).

• decompose (bool) – If True, the circuit is decomposed before printing (default: False).

• kwargs – Additional arguments from Qiskit’s QuantumCircuit.draw() function.

Returns:

Returns the circuit in qiskit QuantumCircuit.draw() format

generate_initial_parameters(seed: int | None = None) → ndarray

Generates random parameters for the encoding circuit

Parameters:

seed (Union[int,None]) – Seed for the random number generator (default: None)

Returns:

The randomly generated parameters

get_circuit(features: ParameterVector | ndarray, parameters: ParameterVector | ndarray = None) → QuantumCircuit

Returns the quantum circuit of the Random Layered encoding circuit.

Parameters:

• features (Union[ParameterVector, np.ndarray]) – The input features.

• parameters (Union[ParameterVector, np.ndarray]) – The trainable parameters of the circuit (not used, since there are no free parameters).

Returns:

The quantum circuit of the Random Layered encoding circuit.

Return type:

QuantumCircuit

get_params(deep: bool = True) → dict

Returns hyper-parameters and their values of the Random Layered encoding circuit

Parameters:

deep (bool) – If True, also the parameters for contained objects are returned (default=True).

Returns:

Dictionary with hyper-parameters and values.

set_params(**params) → EncodingCircuitBase

Sets value of the random layered encoding circuit hyper-parameters.

The random circuit is regenerated with the new hyper-parameters.

Parameters:

params – Hyper-parameters and their values, e.g. num_qubits=2.