Computational intelligence techniques inspired by evolution, by nature, and by the brain are playing important role in the solution of complex real-world problems. Fusion of computational intelligence techniques integrates neural networks, fuzzy systems, and evolutionary computing into system design that enables handling of complexity and managing of uncertainty and imprecision. Each respective technique enhances the capability of the other and the fusion of these paradigms in system design offsets the demerits of one paradigm by the merits of another.

Recently, computational intelligence techniques have been widely applied to a wide variety of complex problems, including engineering, science, and business. However, due to complexity and uncertainty in these problems, it becomes difficult to find out the optimal solution of the problems. Hereby it is necessary to consider the latest trends and developments in the field of fusion of computational intelligence techniques and to develop efficient computational models for solving practical problems. Fusion of computational intelligence techniques covers the spectrum of applications, comprehensively demonstrating the advantages of fusion techniques in industrial applications that deal with various kinds of inaccuracies and uncertainties.

The aim of this special issue is to present research articles as well as review articles that investigate the fusion of computational intelligence techniques, design computational models, and evaluate their outcomes. We are particularly interested in articles describing the new structures, algorithms, and advances in the design of system based on fusion of neural networks, fuzzy systems, and evolutionary algorithms.

Potential topics include, but are not limited to:

• Mathematical foundations of computational models based on the fusion of computational intelligence techniques
• Fusion of neural network and fuzzy systems
• Fusion of fuzzy systems and evolutionary algorithms
• Fusion of neural network and evolutionary algorithms
• Fusion of neural network, fuzzy systems, and evolutionary algorithms
• Fusion of statistical methods and computational intelligence techniques
• Learning theory (derivative based, derivative free)
• Practical application of computational intelligence techniques in engineering, science, and business