This chapter covers
- Introducing swarm intelligence
- Understanding the continuous particle swarm optimization algorithm
- Understanding binary particle swarm optimization
- Understanding permutation-based particle swarm optimization
- Adapting particle swarm optimization for a better trade-off between exploration and exploitation
- Solving continuous and discrete problems using particle swarm optimization
In the treasure-hunting mission I introduced in chapter 2, suppose you want to collaborate and share information with your friends instead of doing the treasure- hunting alone. However, you do not want to follow a competitive approach in which you only keep better-performing hunters and recruit new hunters to replace poorer-performing ones, like in the genetic algorithm (GA) explained in the previous chapters. You want to adopt a more cooperative approach and keep all the hunters, without replacing any, but you want to give more weight to the better-performing hunters and try to emulate their success. This scenario uses swarm intelligence and corresponds to population-based optimization algorithms such as particle swarm optimization (PSO), ant colony optimization (ACO), and artificial bee colony (ABC) algorithms, which will be explained in this fourth part of the book.