qiskit.aqua.components.neural_networks.DiscriminativeNetwork

class DiscriminativeNetwork

Base class for discriminative Quantum or Classical Neural Networks.

This method should initialize the module but raise an exception if a required component of the module is not available.

abstract __init__()

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

Methods

__init__()	Initialize self.
get_label(x)	Apply quantum/classical neural network to the given input sample and compute the respective data label
loss(x, y[, weights])	Loss function used for optimization
set_seed(seed)	Set seed.
train(data, weights[, penalty, …])	Perform one training step w.r.t to the discriminator’s parameters

abstract get_label(x)

Apply quantum/classical neural network to the given input sample and compute the respective data label

Parameter

x (Discriminator) – input, i.e. data sample.

Verursacht

NotImplementedError – not implemented

abstract loss(x, y, weights=None)

Loss function used for optimization

Parameter

• x (Discriminator) – output.

• y (Label) – the data point

• weights (numpy.ndarray) – Data weights.

Rückgabe

Loss w.r.t to the generated data points.

Verursacht

NotImplementedError – not implemented

abstract set_seed(seed)

Set seed.

Parameter

seed (int) – seed

Verursacht

NotImplementedError – not implemented

abstract train(data, weights, penalty=False, quantum_instance=None, shots=None)

Perform one training step w.r.t to the discriminator’s parameters

Parameter

• data (numpy.ndarray) – Data batch.

• weights (numpy.ndarray) – Data sample weights.

• penalty (bool) – Indicate whether or not penalty function is applied to the loss function. Ignored if no penalty function defined.

• quantum_instance (QuantumInstance) – used to run Quantum network. Ignored for a classical network.

• shots (int) – Number of shots for hardware or qasm execution. Ignored for classical network

Rückgabe

with Discriminator loss and updated parameters.

Rückgabetyp

dict

Verursacht

NotImplementedError – not implemented