SamplingNeuralNetwork.probability_gradients¶
- SamplingNeuralNetwork.probability_gradients(input_data, weights)[ソース]¶
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.
- パラメータ:
input_data (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 (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.
- 戻り値:
The probability gradients.
- 戻り値の型: