Computational intelligence (CI) focuses on the theory, design, application, and development of biologically and linguistically motivated computational paradigms combining elements of learning, adaptation, evolution and fuzzy logic.
Computational intelligence originally developed as a branch of artificial intelligence but now it has a large enough extent to be recognized as a separate domain of research. In general, typical artificial intelligence techniques are top-to-bottom where, i.e., the structure of models, solutions, etc. is imposed from above. Computational intelligence techniques are generally bottom-up, where order and structure emerges from an unstructured beginning.
The areas covered by the term computational intelligence include: neural networks, connectionist systems, genetic algorithms, evolutionary programming, fuzzy systems, swarm intelligence, artificial immune systems and hybrid intelligent systems in which these paradigms are contained.
Computational intelligence is also closely related to soft computing, which indicates the difference from operations research, also known as hard computing. With similar problem domains, soft computing puts no conditions on the problem but also provides no guarantees for success, a deficiency which is compensated by the robustness of the methods.