Training and application of process neural network based on quantum-behaved evolutionary algorithm
Zhang Qiang, Panchi Li · 2012
Aiming at the problem that it is difficult for BP algorithm to converge because of more parameters in training of process neural networks based on orthogonal basis expansion, a quantum-behaved evolutionary algorithm is presented which combines the quantum theory and is to train the process neural network. The algorithm using the Pauli matrices to establish the axis of rotation, using qubits in Bloch sphere to rotate around the axis method to carry out optimal search, using the Hadamard gate achieve individual variability to avoid premature, and effectively overcomes the complex compute and easily plunges into local minimums about BP algorithm. Taking network traffic prediction as an application, the simulation results show that the algorithm is validity.