SamplingNeuralNetwork¶
- class SamplingNeuralNetwork(num_inputs, num_weights, sparse, sampling, output_shape, input_gradients=False)[소스]¶
기반 클래스:
NeuralNetwork
A sampling neural network abstract class for all (quantum) neural networks within Qiskit’s machine learning module that generate samples instead of (expected) values.
- 매개변수:
num_inputs (int) – The number of input features.
num_weights (int) – The number of trainable weights.
sparse (bool) – Returns whether the output is sparse or not.
sampling (bool) – Determines whether the network returns a batch of samples or (possibly sparse) array of probabilities in its forward pass. In case of probabilities, the backward pass returns the probability gradients, while it returns (None, None) in the case of samples.
output_shape (int | Tuple[int, ...]) – The shape of the output.
input_gradients (bool) – Determines whether to compute gradients with respect to input data. Note that this parameter is
False
by default, and must be explicitly set toTrue
for a proper gradient computation when usingTorchConnector
.
- 예외 발생:
QiskitMachineLearningError – Invalid parameter values.
Attributes
Returns whether gradients with respect to input data are computed by this neural network in the
backward
method or not.Returns the number of input features.
Returns the number of trainable weights.
Returns the output shape.
Returns:
True
if the network returns a batch of samples andFalse
if a sparse vector (dictionary) of probabilities in its forward pass.Returns whether the output is sparse or not.
Methods
backward
(input_data, weights)Backward pass of the network.
forward
(input_data, weights)Forward pass of the network.
probabilities
(input_data, weights)Histogram (as dict) of the samples from the network.
probability_gradients
(input_data, weights)Probability gradients of histogram resulting from the network.
sample
(input_data, weights)Samples from the network.