EffectiveDimension¶
- class EffectiveDimension(qnn, weight_samples=1, input_samples=1)[source]¶
Bases :
object
This class computes the global effective dimension for a Qiskit
NeuralNetwork
following the definition used in [1].References [1]: Abbas et al., The power of quantum neural networks. The power of QNNs.
- Paramètres
qnn (
NeuralNetwork
) – A QiskitNeuralNetwork
, with a specific dimension(num_weights)
that will determine the shape of the Fisher Information Matrix(num_input_samples * num_weight_samples, num_weights, num_weights)
used to compute the global effective dimension for a set ofinput_samples
, of shape(num_input_samples, qnn_input_size)
, andweight_samples
, of shape(num_weight_samples, num_weights)
.weight_samples (
Union
[ndarray
,int
]) – An array of neural network parameters (weights), of shape(num_weight_samples, num_weights)
, or anint
to indicate the number of parameter sets to sample randomly from a uniform distribution. By default,weight_samples = 1
.input_samples (
Union
[ndarray
,int
]) – An array of samples to the neural network, of shape(num_input_samples, qnn_input_size)
, or anint
to indicate the number of input sets to sample randomly from a normal distribution. By default,input_samples = 1
.
Attributes
Returns network input samples.
Returns network weight samples.
Methods
get_effective_dimension
(dataset_size)This method computes the effective dimension for a dataset of size
dataset_size
.get_fisher_information
(gradients, model_outputs)This method computes the average Jacobian for every set of gradients and model output as shown in Abbas et al.
get_normalized_fisher
(normalized_fisher)This method computes the normalized Fisher Information Matrix and extracts its trace.
This method computes the model's Monte Carlo sampling for a set of input samples and weight samples.