Social programming using functional swarm optimization

The development of mathematical neural networks was based on an analogy with biological neural networks found in nature. Recently there has been a resurgence in research and understanding in self-organizing networks that are based on other metaphors: genetics, immune systems etc. In this paper a new methodology is presented for creating Complex Adaptive Functional Networks (CAFN) that are based on the Particle Swarm socialpsychological metaphor. The proposed Social Programming methodology is base on combining the Particle Swarm methodology with The Group Method of Data Handling and Cartesian Programming. Keywords— Social Programming, Cartesian Programming, Genetic Programming, Particle Swarm Optimization, Functional Swarm Optimization. I. Particle Swarm Optimization The Particle Swarm Algorithm is an adaptive algorithm based on a social-psychological metaphor [1]. A population of individuals adapt by returning stochastically toward previously successful regions in the search space, and are influenced by the successes of their topological neighbors. Most particle swarms are based on two sociometric principles. Particles fly through the solution space and are influenced by both the best particle in the particle population and the best solution that a current particle has discovered so far. The best particle in the population is typically denoted by (global best), while the best position that has been visited by the current particle is denoted by (local best). The (global best) individual conceptually connects all members of the population to one another. That is, each particle is influenced by the very best performance of any member in the entire population. The (local best) individual is conceptually seen as the ability for particles to remember past personal successes. Particle Swarm Optimization is a relatively new addition to the evolutionary computation methodology [2] [3][1] [4] [5] [6] [7], but the performance of PSO has been shown to be competitive with more mature methodologies [7] [8] [9]. Since it is relatively straightforward to extend PSO by attaching mechanisms employed by other evolutionary computation methods that increase their performance, PSO has the potential to become an excellent framework for building custom high-performance stochastic optimizers[10]. It is interesting to note that PSO can be considered as a form of continuous-valued Cellular Automata. This allows its hybridizations to extend into areas other than computational intelligence[1].