>Introduction >Background and Method >Demo >Application >Comparison with GA >Artificial Intelligence > References
Particle Swarm Optimization ( PSO ) : Comparison with Genetic Algorithms
Both the systems are initialized with a random population / agents , and a search is made for the optimum by updating generations .
However , in PSO we do not use evolutionary operators like crossover , mutation etc . In this case , the particles fly through the space by following current optimum particles , Compared to Genetic Algorithms , PSO is easier to implement and there are fewer parameters to adjust .
Both PSO and GA use some amount of randomization in decision making . PSO is highly dependant on stochastic processes like Evolutionary Computing . The adjustment towards gbest and pbest is somewhat similar to the crossover operator . It uses the idea of fitness . However , the unique idea is to 'fly' through the space in search for a better solution .
>Introduction >Background and Method >Demo >Application >Comparison with GA >Artificial Intelligence > References