Deep swarm: Nested particle swarm optimization

A new generation of particle swarm optimization (PSO) has been developed that automatically evolves optimal or near-optimal values for parameters of the PSO algorithm such as population size and neighborhood size, and, if used, parameters of associated neural network(s), such as number of hidden processing elements (PEs). Called Deep Swarm, it is a nested version of PSO, and comprises swarms within a swarm.