Fuente: WIPO "tomato" A method of performing computation in a hybrid quantum-classical computing system includes executing one or more iterations, each iteration including receiving input features of a training sample in a first classical neural network, computing first outputs based on first trainable parameters, setting a quantum processor in an initial state, applying a parametrized quantum circuit to the quantum processor based on the first outputs and a set of variational parameters, the parametrized quantum circuit including encoding layer circuits based on the first outputs, and trainable layer circuits based on the set of variational parameters, and measuring qubit states of the quantum processor, receiving measured expectation values of the qubit states in a second classical neural network, computing second outputs based second trainable parameters, adjusting the first trainable parameters, the plurality of second trainable parameters, and the set of variational parameters.