Swarm Algorithms 101

Swarm algorithms

Swarm intelligence (swarm algorithms) is the study of computer systems inspired by “collective intelligence”. Collective intelligence emerges through the cooperation of a large number of homogeneous agents in the environment. Examples include schools of fish, flocks of birds and colonies of ants. This intelligence is decentralized, self-organized and distributed across an environment. In nature, such systems are commonly used to solve problems such as efficient foraging, prey escape, or colony displacement.

Information is usually stored in all participating homogeneous agents, or is stored or communicated in the environment itself, for example through the use of pheromones in ants, dancing in bees, and proximity in fish and bees. birds.

As a group, simple creatures following simple rules can display a surprising amount of complexity, efficiency, and even creativity. Known as swarm intelligence, this trait is found in nature, but researchers have recently started using it to transform various fields such as robotics, data mining, medicine and blockchains.

Ants, for example, can perform only a limited range of functions, but an ant colony can build bridges, create highways of food and information, wage war, and enslave other species of ants. – all of this is beyond the comprehension of a single ant. Likewise, schools of fish, flocks of birds, beehives, and other species exhibit behavior indicative of planning by a higher intelligence that does not actually exist.

This happens through a process called stigmergy. Simply put, a small change by one member of the group causes the other members to behave differently, leading to a new pattern of behavior.

When an ant finds a food source, it marks the path with pheromones. This attracts other ants to that path, leads them to the food source, and prompts them to mark the same path with more pheromones. Over time, the most efficient route will become the highway, because the faster and easier a path, the more ants will reach the food and the more pheromones will be on the way. Thus, it seems that a smarter being has chosen the best path, but it has emerged from the tiny and simple changes made by individuals.

The paradigm consists of two dominant subfields 1) Ant Colony Optimization which studies probabilistic algorithms inspired by the stigmergy and foraging behavior of ants, and 2) Particle Swarm Optimization which studies probabilistic algorithms inspired by the herd, the schools of fish and the breeding. Like evolutionary computing, swarm intelligence algorithms or strategies are considered adaptive strategies and are generally applied to research and optimization domains.