Chapter Preview
TopIntroduction
This paper introduces computational intelligence and describes its aims and its main components. Then it focuses on the definition of hybrid intelligent systems and briefly describes the most popular among them. The increased popularity of hybrid intelligent systems during the last decade, is due to the extensive success of these systems in a wide range of real-world complex problems, but also has to do with the increased capabilities of computational technology. One of the reasons for this success has to do with the synergy derived by the computational intelligent components, such as machine learning, fuzzy logic, neural networks, genetic algorithms, or other intelligent algorithms and techniques. Each of the partial methodologies provides hybrid systems with complementary reasoning and searching methods that allow the use of domain knowledge and empirical data to solve complex problems.
Key Terms in this Chapter
Computational Intelligence: A set of intelligent computational approaches to address complex real-world problems to which traditional modeling approaches explicit statistical modelling are ineffective or infeasible.
Machine Learning: A branch of artificial intelligence which concerns the construction and study of systems that can learn from data.
Hybrid Intelligence: The development of software systems which employ, in parallel, a combination of methods and techniques from artificial intelligence subfields as neuro-fuzzy systems, fuzzy expert systems, evolutionary neural networks, genetic fuzzy systems, etc.
Evolutionary Computation: Involves continuous and combinatorial optimization. Its algorithms can be considered global optimization methods of metaheuristic or stochastic nature, proper for solving black box problems.
Fuzzy Logic: A form of many-valued logic which deals with approximate reasoning.
Data Mining: An interdisciplinary subfield of computer science that corresponds to the computational process of discovering patterns in large data collections.
Nature-Inspired Intelligence: The development of computational models and algorithms inspired from natural intelligence found in physical, chemical, social and biological systems, for solving various practical engineering problems.