Abstract
In this paper, we present a bio-inspired learning methodology based on swarm particle optimization to learn both weights and topology of a multilayer feedforward neural network. The training algorithm represents a novel adaptive version of the particle swarm algorithm where the inertia weight is improved to increase the accuracy of the neural network. In addition to the updated exploration parameter, the proposed algorithm encloses a new acceleration parameter to deal with the convergence rate. In fact, the adopted optimization strategy aims to simulate a mutation rate with higher values in the favor of a global search. The swarm-based feedforward neural network was tested with benchmarking problems which includes both classification and regression problems. Some results are also presented to evaluate the algorithm performances.