Talk to someone unfamiliar with the work of artificial intelligence about evolutionary algorithms and you may get a blank stare or, at best, an look of bewilderment and a subsequent inquiry about what exactly the phrase means. Once explained, the concept may provide a bit of insight–to be sure, evolutionary algorithms are defined as a subset of evolutionary computation, a generic population-based metaheuristic optimization algorithm, which uses mechanisms inspired by biological evolution–but not many are aware, or fail to consider, that they’ve encountered such many times, in various forms.
Take, for instance, genetic algorithms, which are a type evolutionary algorithm that is a search heuristic mimicking the process of natural selection. The purpose is to generate solutions to optimization problems using techniques inspired by natural evolution. This video is explains it in full, in under five minutes:
Below, I’ve included some of the most common things which use or include genetic algorithms:
Computer Gaming
Online gaming is highly popular–so popular that the number of individuals who participate engage in gaming around the world, account for over 44% of the total number of people online, at 700 million gamers in 2013. Offline, games are equally popular, with people simply using their devices create wholly different worlds from their own, such as The Sims, which has won a Guinness record for being the best selling PC game of all time. The game, now in its in 16th year, uses genetic algorithms instead of having users play against humans online. Instead, The Sims is programmed to learn and incorporate strategies from previous games in which users have been successful, using game theory.
Finance
Financial markets are always changing. Genetic algorithms help deal with nonlinear problems of trading. Investopedia describes it this way: “Genetic algorithms are created mathematically using vectors, which are quantities that have direction and magnitude. Parameters for each trading rule are represented with a one-dimensional vector that can be thought of as a chromosome in genetic terms. Meanwhile, the values used in each parameter can be thought of as genes, which are then modified using natural selection.”
Cars
Race cars are not necessarily designed for everyday travel. Instead, they are crafted for sport and the ability to reach high speeds. A large part of their functionality are a result of design. Airplanes as well, created to travel high altitudes at fast speeds, need to be designed well. Genetic algorithms provide combinations of materials that would work best, from an engineering perspective, which then enables designers to put them together and save time on continuous testing.
These are just a few examples of how people interact with genetic algorithms very often. As our abilities in science continue to evolve, applications and the prevalence of such will likely continue to grow. For a full list of uses, be sure to visit this blog from Brainz.org and share with friends.