摘要：In our society the amount of data doubles almost every year. Hence, there is an urgent need for a new generation of computationally intelligent techniques and tools to assist humans in extracting useful information (knowledge) from the rapidly growing volume of data. When we attempt to solve real-world problems, like extracting knowledge from large amount of data, we re- alize that they are typically ill-defined systems, difficult to model and with large-scale solution spaces. In these cases, precise models are impractical, too expensive, or non-existent. Furthermore, the relevant available informa- tion is usually in the form of empirical prior knowledge and input–output data representing instances of the sys- tem’sbehavior. Therefore, weneed an approximatereason- ingsystem capableofhandlingsuchimperfectinformation. While Bezdek [2] defines such approaches within a frame called computational intelligence, Zadeh [3] explains the same using the soft computing paradigm. According to Zadeh ”... in contrast to traditional, hard computing, soft computing is tolerant of imprecision, uncertainty, and par- tial truth.” In this context Fuzzy Logic (FL), Probabilistic Reasoning (PR), Neural Networks (NNs), and Evolution- ary Algorithms (EAs) are considered as main components of CI. Each of these technologies provide us with comple- mentary reasoning and searching methods to solve com- plex, real-world problems. What is important to note is that soft computing is not a melange. Rather, it is a part- nership in which each of the partners contributes a distinct methodology for addressing problems in its domain. In this perspective, the principal constituent methodologies in CI are complementary rather than competitive
