Training and application of process neural network based on quantum shuffled frog leaping algorithm

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 shuffled frog leaping algorithm is presented which combines the quantum theory and is to train the process neural network. In this algorithm, the individuals are expressed with Bloch spherical coordinates of qubits. The quantum individuals are updated by quantum rotation gates, and the mutation of individuals is achieved with Hadamard gates. For the size and direction of rotation angle of quantum rotation gates, a simple determining method is proposed. Above operations extend the search of the solution space effectively. To predict sunspot as an example to validate the presented algorithm.