Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing

1

Introduction to Computational Intelligence

Keep it simple:

As simple as possible,

But not simpler.

–Albert Einstein

1.1 Computational Intelligence

Much is unknown about intelligence and much will remain beyond human comprehension. The fundamental nature of intelligence is only poorly understood and even the definition of intelligence remains a subject of controversy. Considerable research is currently being devoted to the understanding and representation of intelligence. According to its dictionary definition, intelligence means the ability to comprehend, reason and learn. From this point of view, a definition of intelligence can be elicited whereby an intelligent system is capable of comprehending (with or without much a priori information) the environment or a process; reasoning about and identifying different environmental or process variables, their inter-relationship and influence on the environment or process; and learning about the environment or process, its disturbance and operating conditions. Other aspects of intelligence that describe human intelligence are creativity, skills, consciousness, intuition and emotion.

Traditional artificial intelligence (AI) has tried to simulate such intelligent behaviour in systems requiring exact and complete knowledge representation (Turing, 1950). Unfortunately, many real-world systems cannot be described exactly with complete knowledge. It has been demonstrated that the use of highly complex mathematical description can seriously ...