French
Langues
English
Bengali
French
Hindi
Italian
Japanese
Korean
Malayalam
Russian
Spanish
Tamil
Turkish
Vietnamese
Shortcuts



SamplingNeuralNetwork.probability_gradients

SamplingNeuralNetwork.probability_gradients(input_data, weights)[source]

Probability gradients of histogram resulting from the network. Format depends on the set interpret function. Shape is (input_grad, weights_grad), where each grad has one dict for each parameter and each dict contains as value the derivative of the probability of measuring the key.

Paramètres
  • input_data (Union[List[float], ndarray, float, None]) – input data of the shape (num_inputs). In case of a single scalar input it is directly cast to and interpreted like a one-element array.

  • weights (Union[List[float], ndarray, float, None]) – trainable weights of the shape (num_weights). In case of a single scalar weight it is directly cast to and interpreted like a one-element array.

Type renvoyé

Tuple[Union[ndarray, SparseArray], Union[ndarray, SparseArray]]

Renvoie

The probability gradients.