- TwoLayerQNN.backward(input_data, weights)¶
Backward pass of the network.
array. (it is directly cast to and interpreted like a one-element) –
The result of the neural network of the backward pass, i.e., a tuple with the gradients for input and weights of shape (output_shape, num_input) and (output_shape, num_weights), respectively.
- 반환 형식:
tuple[np.ndarray | SparseArray | None, np.ndarray | SparseArray | None]