||Particle swarm optimization is a population based optimization algorithm where particles move in the solution space under the principles of sociology, psychology and bionomics. The stochastic and social nature of this algorithm has proven useful in avoiding getting trapped in local minima. For this reason it has been successfully applied in many different areas since the last decade, e.g. training of neural networks, scheduling problems and image registration, just to name a few. In this seminar, we will talk about some variants of particle swarm optimization and its application to retinal image registration. We will also put some emphasis on how to select parameters for this algorithm.