Rakitianskaia, A.S. (Anastassia Sergeevna)Engelbrecht, Andries P.2012-12-112012-12-112012-09Rakitianskaia, AS & Engelbrecht, AP 2012, 'Training feedforward neural networks with dynamic particle swarm optimisation', Swarm Intelligence, vol. 6, no. 3, pp. 233-270, doi: 10.1007/s11721-012-0071-61935-3812 (print)1935-3820 (online)10.1007/s11721-012-0071-6http://hdl.handle.net/2263/20669Particle swarm optimisation has been successfully applied to train feedforward neural networks in static environments.Many real-world problems to which neural networks are applied are dynamic in the sense that the underlying data distribution changes over time. In the context of classification problems, this leads to concept drift where decision boundaries may change over time. This article investigates the applicability of dynamic particle swarm optimisation algorithms as neural network training algorithms under the presence of concept drift.en© Springer Science + Business Media, LLC 2012. The original publication is available at www.springerlink.comSwarm intelligenceParticle swarm optimization (PSO)Neural networksDynamic environmentsClassificationConcept driftTraining feedforward neural networks with dynamic particle swarm optimisationPostprint Article