The Artificial Intelligence community sought to understand human intelligence by building computer programs that exhibit intelligent behavior. Intelligence was perceived as a problem-solving ability. Most human problems seem to be motivated, instead of mathematical solutions. The diagnosis of an illness could not be calculated. If a patient had a group of symptoms, then she had a particular disease. However, such reasoning requires prior knowledge. The programs needed for the "knowledge" that the disease showed a particular group of symptoms. For the AI ??community, that vague knowledge residing in the minds of "experts" was more than textbook knowledge. So they called the programs that solve these problems, expert systems.

Expert systems managed object-oriented problem solving tasks, including diagnosis, planning, programming, configuration and design. One of the methods of knowledge representation was through "Yeah, well ..." rules. When the "if" part of a rule is fulfilled, then the "continuation" of the rule is concluded. These became the rule-based expert systems. But knowledge of facts sometimes and sometimes, inaccurate. knowledge of facts was a clear case of cause and effect, clear conclusions can be drawn from specific standards. The pain was a symptom of a disease. If the disease always show the pain, then pain pointed to the disease. But the vague knowledge and judgments are called heuristic knowledge. It was rather an art. The pain symptom could not mechanically point to disease, which occasionally exhibited pain. The uncertainty did not give concrete answers.

The AI ??community tried to resolve this problem by suggesting a statistical analysis or heuristic uncertainty. The possibilities were represented by real numbers or sets of vectors of real value. The vectors were evaluated by means of different "fuzzy" concepts. The components of the measurements were listed, giving the basis of numerical values. Variations were combined, using methods for calculating the combination differences. The combined uncertainty and its components are expressed in the form of standard deviations. " The uncertainty was given a mathematical expression, which was very unhelpful in the diagnosis of disease.

The human mind does not compute mathematical relationships to assess the uncertainty. The mind knew that a particular symptom, said one possibility, it uses intuition, a process of elimination, to immediately identify the patterns. Vago was powerfully useful information for a process of elimination, as it eliminates many other possibilities. If the patient had no pain, all diseases which always exhibited pain could be eliminated. Disease, which sometimes exhibit the pain remained. Other symptoms helped identify a very small database. A selection was easier for a smaller group. Uncertainty can be powerfully useful for a process of elimination.

Intuition is an algorithm that evaluated the entire database, eliminating all contexts that do not fit. This algorithm has driven expert systems that moved quickly to recognize a disease, identify a case or diagnose the problems of a complex machine. Was instantaneous and global, and logical. If several parallel answers could be presented, as in the many parameters of a power plant, recognition was instant. For the mind, where millions of parameters were presented at the same time, real time pattern recognition was practical. And the elimination of key conclusively that could handle the uncertainty, without resort to abstruse calculations.