Evolutionary algorithm

Two-population EA search (2)

Evolutionary algorithm (EA) is a subset of evolutionary computation, a generic population-based metaheuristic optimization algorithm. An EA uses mechanisms inspired by biological evolution, such as reproduction, mutation, recombination, and selection. Candidate solutions to the optimization problem play the role of individuals in a population, and the fitness function determines the quality of the solutions (or individuals). The evolution usually starts from a population of randomly generated individuals and happens in generations. In each generation, the fitness of every individual in the population is evaluated, multiple individuals are stochastically selected from the current population (based on their fitness), and modified (recombined and possibly randomly mutated) to form a new population. The new population is then used in the next iteration of the algorithm. Commonly, the algorithm terminates when either a maximum number of generations has been produced, or a satisfactory fitness level has been reached for the population. If the algorithm has terminated due to a maximum number of generations, a satisfactory solution may or may not have been reached.

Evolutionary algorithms are categorized into several types, including but not limited to:

• Genetic algorithms (GAs), which simulate the process of natural selection where the fittest individuals are selected for reproduction in order to produce offspring of the next generation.
• Genetic programming (GP), which evolves computer programs, typically tree-like graph structures, by means of natural selection and genetic operators.
• Evolution strategies (ES), which focus more on the optimization of real-valued parameters by mimicking the process of natural evolution.
• Differential evolution (DE), a method that optimizes a problem by iteratively trying to improve a candidate solution with regard to a given measure of quality.
• Evolutionary programming (EP), similar to evolution strategies, but focuses on the evolution of structures, such as neural networks or finite state machines, rather than numeric optimization.

Applications

Evolutionary algorithms have been applied to a wide range of problems, from optimization problems, which are their most common application, to automatic programming, machine learning, economics, artificial life, and robotics. They are particularly useful in problems where the solution space is complex, poorly understood, or where traditional optimization methods fail.

Advantages and Disadvantages

The main advantage of evolutionary algorithms is their ability to find good solutions to complex problems where other methods fail. They are flexible and can be adapted to different types of optimization problems. However, EAs can be computationally expensive, and there is no guarantee that they will find the global maximum or minimum.

See Also

• Artificial intelligence
• Machine learning
• Optimization (mathematics)
• Simulated annealing
• Swarm intelligence

This article is a stub. You can help WikiMD by registering to expand it. Editing is available only to registered and verified users. WikiMD is a comprehensive, free health & wellness encyclopedia.