Swarm intelligence (SI) comes from swarm behavior existing in nature. It refers to the intelligent cooperation behaviors in a group which is formed by many simple individuals. An individual’s behavior is simple, but through cooperation, the group which consists of simple individuals can perform global behavior to solve complex tasks in nature. Machine learning (ML) is a science of the artificial, and it is a study of how a computer can simulate or achieve learning behavior of human. Generalization is the most central concept in machine learning, and it can perform well on unseen data instances.

Recently, SI and ML have attracted close attention of researchers and have also been applied successfully in many fields (e.g. engineering, transportation, commerce, industry and so on). However, there are still huge space for improvement about SI algorithms and ML algorithms. On one hand, SI algorithms (e.g. ant colonies, bird flocking and so on) are often limited by weak points of computation time and local solution for large and complex problems. On other hand, ML algorithms are often limited by weak points of data and parameters.

This Special Issue welcomes original research and review articles on the theory and application of swarm intelligence and machine learning.

Potential topics include but are not limited to the following:

• Benchmarking and evaluation of new SI algorithms and ML algorithms
• Convergence proof for SI algorithms and ML algorithms
• Comparative theoretical and empirical studies on SI algorithms
• Ant colony optimization
• Particle swarm optimization
• Artificial bee swarm algorithm
• Bacterial foraging optimization
• Artificial fish algorithm
• Support Vector Machine
• Neural Networks
• SI algorithms and ML algorithms for real-world applications