SamplingNeuralNetwork.probability_gradients¶
- SamplingNeuralNetwork.probability_gradients(input_data, weights)[소스]¶
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.
- 매개변수
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.
- 반환 형식
Tuple
[Union
[ndarray
,SparseArray
],Union
[ndarray
,SparseArray
]]- 반환
The probability gradients.