Neural networks learning using vbest model particle swarm optimisation

The two most commonly used methods are known as gbest model and lbest model in particle swarm optimization (PSO). The gbest model converges quickly on problem solutions but has a weakness of becoming trapped in local optima, while the lbest model is able to "flow around" local optima, as the individuals explore different regions. In this paper, we investigated a variable neighborhood model in particle swarm search method for neural network learning, and the experimental results illustrated its efficiency.